Pandas 中文参考指南

In [1]: import pandas as pd

In [2]: from io import StringIO

In [3]: data = "col1,col2,col3\na,b,1\na,b,2\nc,d,3"

In [4]: pd.read_csv(StringIO(data))
Out[4]:
  col1 col2  col3
0    a    b     1
1    a    b     2
2    c    d     3

In [5]: pd.read_csv(StringIO(data), usecols=lambda x: x.upper() in ["COL1", "COL3"])
Out[5]:
  col1  col3
0    a     1
1    a     2
2    c     3

In [6]: data = "col1,col2,col3\na,b,1\na,b,2\nc,d,3"

In [7]: pd.read_csv(StringIO(data))
Out[7]:
  col1 col2  col3
0    a    b     1
1    a    b     2
2    c    d     3

In [8]: pd.read_csv(StringIO(data), skiprows=lambda x: x % 2 != 0)
Out[8]:
  col1 col2  col3
0    a    b     2

In [9]: import numpy as np

In [10]: data = "a,b,c,d\n1,2,3,4\n5,6,7,8\n9,10,11"

In [11]: print(data)
a,b,c,d
1,2,3,4
5,6,7,8
9,10,11

In [12]: df = pd.read_csv(StringIO(data), dtype=object)

In [13]: df
Out[13]:
   a   b   c    d
0  1   2   3    4
1  5   6   7    8
2  9  10  11  NaN

In [14]: df["a"][0]
Out[14]: '1'

In [15]: df = pd.read_csv(StringIO(data), dtype={"b": object, "c": np.float64, "d": "Int64"})

In [16]: df.dtypes
Out[16]:
a      int64
b     object
c    float64
d      Int64
dtype: object

In [17]: data = "col_1\n1\n2\n'A'\n4.22"

In [18]: df = pd.read_csv(StringIO(data), converters={"col_1": str})

In [19]: df
Out[19]:
  col_1
0     1
1     2
2   'A'
3  4.22

In [20]: df["col_1"].apply(type).value_counts()
Out[20]:
col_1
<class 'str'>    4
Name: count, dtype: int64

In [21]: df2 = pd.read_csv(StringIO(data))

In [22]: df2["col_1"] = pd.to_numeric(df2["col_1"], errors="coerce")

In [23]: df2
Out[23]:
   col_1
0   1.00
1   2.00
2    NaN
3   4.22

In [24]: df2["col_1"].apply(type).value_counts()
Out[24]:
col_1
<class 'float'>    4
Name: count, dtype: int64

In [25]: col_1 = list(range(500000)) + ["a", "b"] + list(range(500000))

In [26]: df = pd.DataFrame({"col_1": col_1})

In [27]: df.to_csv("foo.csv")

In [28]: mixed_df = pd.read_csv("foo.csv")

In [29]: mixed_df["col_1"].apply(type).value_counts()
Out[29]:
col_1
<class 'int'>    737858
<class 'str'>    262144
Name: count, dtype: int64

In [30]: mixed_df["col_1"].dtype
Out[30]: dtype('O')

In [31]: data = """a,b,c,d,e,f,g,h,i,j
   ....: 1,2.5,True,a,,,,,12-31-2019,
   ....: 3,4.5,False,b,6,7.5,True,a,12-31-2019,
   ....: """
   ....:

In [32]: df = pd.read_csv(StringIO(data), dtype_backend="numpy_nullable", parse_dates=["i"])

In [33]: df
Out[33]:
   a    b      c  d     e     f     g     h          i     j
0  1  2.5   True  a  <NA>  <NA>  <NA>  <NA> 2019-12-31  <NA>
1  3  4.5  False  b     6   7.5  True     a 2019-12-31  <NA>

In [34]: df.dtypes
Out[34]:
a             Int64
b           Float64
c           boolean
d    string[python]
e             Int64
f           Float64
g           boolean
h    string[python]
i    datetime64[ns]
j             Int64
dtype: object

In [35]: data = "col1,col2,col3\na,b,1\na,b,2\nc,d,3"

In [36]: pd.read_csv(StringIO(data))
Out[36]:
  col1 col2  col3
0    a    b     1
1    a    b     2
2    c    d     3

In [37]: pd.read_csv(StringIO(data)).dtypes
Out[37]:
col1    object
col2    object
col3     int64
dtype: object

In [38]: pd.read_csv(StringIO(data), dtype="category").dtypes
Out[38]:
col1    category
col2    category
col3    category
dtype: object

In [39]: pd.read_csv(StringIO(data), dtype={"col1": "category"}).dtypes
Out[39]:
col1    category
col2      object
col3       int64
dtype: object

In [40]: from pandas.api.types import CategoricalDtype

In [41]: dtype = CategoricalDtype(["d", "c", "b", "a"], ordered=True)

In [42]: pd.read_csv(StringIO(data), dtype={"col1": dtype}).dtypes
Out[42]:
col1    category
col2      object
col3       int64
dtype: object

In [43]: dtype = CategoricalDtype(["a", "b", "d"])  # No 'c'

In [44]: pd.read_csv(StringIO(data), dtype={"col1": dtype}).col1
Out[44]:
0      a
1      a
2    NaN
Name: col1, dtype: category
Categories (3, object): ['a', 'b', 'd']

In [45]: df = pd.read_csv(StringIO(data), dtype="category")

In [46]: df.dtypes
Out[46]:
col1    category
col2    category
col3    category
dtype: object

In [47]: df["col3"]
Out[47]:
0    1
1    2
2    3
Name: col3, dtype: category
Categories (3, object): ['1', '2', '3']

In [48]: new_categories = pd.to_numeric(df["col3"].cat.categories)

In [49]: df["col3"] = df["col3"].cat.rename_categories(new_categories)

In [50]: df["col3"]
Out[50]:
0    1
1    2
2    3
Name: col3, dtype: category
Categories (3, int64): [1, 2, 3]

In [51]: data = "a,b,c\n1,2,3\n4,5,6\n7,8,9"

In [52]: print(data)
a,b,c
1,2,3
4,5,6
7,8,9

In [53]: pd.read_csv(StringIO(data))
Out[53]:
   a  b  c
0  1  2  3
1  4  5  6
2  7  8  9

In [54]: print(data)
a,b,c
1,2,3
4,5,6
7,8,9

In [55]: pd.read_csv(StringIO(data), names=["foo", "bar", "baz"], header=0)
Out[55]:
   foo  bar  baz
0    1    2    3
1    4    5    6
2    7    8    9

In [56]: pd.read_csv(StringIO(data), names=["foo", "bar", "baz"], header=None)
Out[56]:
  foo bar baz
0   a   b   c
1   1   2   3
2   4   5   6
3   7   8   9

In [57]: data = "skip this skip it\na,b,c\n1,2,3\n4,5,6\n7,8,9"

In [58]: pd.read_csv(StringIO(data), header=1)
Out[58]:
   a  b  c
0  1  2  3
1  4  5  6
2  7  8  9

In [59]: data = "a,b,a\n0,1,2\n3,4,5"

In [60]: pd.read_csv(StringIO(data))
Out[60]:
   a  b  a.1
0  0  1    2
1  3  4    5

In [61]: data = "a,b,c,d\n1,2,3,foo\n4,5,6,bar\n7,8,9,baz"

In [62]: pd.read_csv(StringIO(data))
Out[62]:
   a  b  c    d
0  1  2  3  foo
1  4  5  6  bar
2  7  8  9  baz

In [63]: pd.read_csv(StringIO(data), usecols=["b", "d"])
Out[63]:
   b    d
0  2  foo
1  5  bar
2  8  baz

In [64]: pd.read_csv(StringIO(data), usecols=[0, 2, 3])
Out[64]:
   a  c    d
0  1  3  foo
1  4  6  bar
2  7  9  baz

In [65]: pd.read_csv(StringIO(data), usecols=lambda x: x.upper() in ["A", "C"])
Out[65]:
   a  c
0  1  3
1  4  6
2  7  9

In [66]: pd.read_csv(StringIO(data), usecols=lambda x: x not in ["a", "c"])
Out[66]:
   b    d
0  2  foo
1  5  bar
2  8  baz

In [67]: data = "\na,b,c\n  \n# commented line\n1,2,3\n\n4,5,6"

In [68]: print(data)

a,b,c

# commented line
1,2,3

4,5,6

In [69]: pd.read_csv(StringIO(data), comment="#")
Out[69]:
   a  b  c
0  1  2  3
1  4  5  6

In [70]: data = "a,b,c\n\n1,2,3\n\n\n4,5,6"

In [71]: pd.read_csv(StringIO(data), skip_blank_lines=False)
Out[71]:
     a    b    c
0  NaN  NaN  NaN
1  1.0  2.0  3.0
2  NaN  NaN  NaN
3  NaN  NaN  NaN
4  4.0  5.0  6.0

In [72]: data = "#comment\na,b,c\nA,B,C\n1,2,3"

In [73]: pd.read_csv(StringIO(data), comment="#", header=1)
Out[73]:
   A  B  C
0  1  2  3

In [74]: data = "A,B,C\n#comment\na,b,c\n1,2,3"

In [75]: pd.read_csv(StringIO(data), comment="#", skiprows=2)
Out[75]:
   a  b  c
0  1  2  3

In [76]: data = (
   ....:     "# empty\n"
   ....:     "# second empty line\n"
   ....:     "# third emptyline\n"
   ....:     "X,Y,Z\n"
   ....:     "1,2,3\n"
   ....:     "A,B,C\n"
   ....:     "1,2.,4.\n"
   ....:     "5.,NaN,10.0\n"
   ....: )
   ....:

In [77]: print(data)
# empty
# second empty line
# third emptyline
X,Y,Z
1,2,3
A,B,C
1,2.,4.
5.,NaN,10.0


In [78]: pd.read_csv(StringIO(data), comment="#", skiprows=4, header=1)
Out[78]:
     A    B     C
0  1.0  2.0   4.0
1  5.0  NaN  10.0

In [79]: data = (
   ....:     "ID,level,category\n"
   ....:     "Patient1,123000,x # really unpleasant\n"
   ....:     "Patient2,23000,y # wouldn't take his medicine\n"
   ....:     "Patient3,1234018,z # awesome"
   ....: )
   ....:

In [80]: with open("tmp.csv", "w") as fh:
   ....:     fh.write(data)
   ....:

In [81]: print(open("tmp.csv").read())
ID,level,category
Patient1,123000,x # really unpleasant
Patient2,23000,y # wouldn't take his medicine
Patient3,1234018,z # awesome

In [82]: df = pd.read_csv("tmp.csv")

In [83]: df
Out[83]:
         ID    level                        category
0  Patient1   123000           x # really unpleasant
1  Patient2    23000  y # wouldn't take his medicine
2  Patient3  1234018                     z # awesome

In [84]: df = pd.read_csv("tmp.csv", comment="#")

In [85]: df
Out[85]:
         ID    level category
0  Patient1   123000       x
1  Patient2    23000       y
2  Patient3  1234018       z

In [86]: from io import BytesIO

In [87]: data = b"word,length\n" b"Tr\xc3\xa4umen,7\n" b"Gr\xc3\xbc\xc3\x9fe,5"

In [88]: data = data.decode("utf8").encode("latin-1")

In [89]: df = pd.read_csv(BytesIO(data), encoding="latin-1")

In [90]: df
Out[90]:
      word  length
0  Träumen       7
1    Grüße       5

In [91]: df["word"][1]
Out[91]: 'Grüße'

In [92]: data = "a,b,c\n4,apple,bat,5.7\n8,orange,cow,10"

In [93]: pd.read_csv(StringIO(data))
Out[93]:
        a    b     c
4   apple  bat   5.7
8  orange  cow  10.0

In [94]: data = "index,a,b,c\n4,apple,bat,5.7\n8,orange,cow,10"

In [95]: pd.read_csv(StringIO(data), index_col=0)
Out[95]:
            a    b     c
index
4       apple  bat   5.7
8      orange  cow  10.0

In [96]: data = "a,b,c\n4,apple,bat,\n8,orange,cow,"

In [97]: print(data)
a,b,c
4,apple,bat,
8,orange,cow,

In [98]: pd.read_csv(StringIO(data))
Out[98]:
        a    b   c
4   apple  bat NaN
8  orange  cow NaN

In [99]: pd.read_csv(StringIO(data), index_col=False)
Out[99]:
   a       b    c
0  4   apple  bat
1  8  orange  cow

In [100]: data = "a,b,c\n4,apple,bat,\n8,orange,cow,"

In [101]: print(data)
a,b,c
4,apple,bat,
8,orange,cow,

In [102]: pd.read_csv(StringIO(data), usecols=["b", "c"])
Out[102]:
     b   c
4  bat NaN
8  cow NaN

In [103]: pd.read_csv(StringIO(data), usecols=["b", "c"], index_col=0)
Out[103]:
     b   c
4  bat NaN
8  cow NaN

In [104]: with open("foo.csv", mode="w") as f:
   .....:     f.write("date,A,B,C\n20090101,a,1,2\n20090102,b,3,4\n20090103,c,4,5")
   .....:

# Use a column as an index, and parse it as dates.
In [105]: df = pd.read_csv("foo.csv", index_col=0, parse_dates=True)

In [106]: df
Out[106]:
            A  B  C
date
2009-01-01  a  1  2
2009-01-02  b  3  4
2009-01-03  c  4  5

# These are Python datetime objects
In [107]: df.index
Out[107]: DatetimeIndex(['2009-01-01', '2009-01-02', '2009-01-03'], dtype='datetime64[ns]', name='date', freq=None)

In [108]: data = (
   .....:     "KORD,19990127, 19:00:00, 18:56:00, 0.8100\n"
   .....:     "KORD,19990127, 20:00:00, 19:56:00, 0.0100\n"
   .....:     "KORD,19990127, 21:00:00, 20:56:00, -0.5900\n"
   .....:     "KORD,19990127, 21:00:00, 21:18:00, -0.9900\n"
   .....:     "KORD,19990127, 22:00:00, 21:56:00, -0.5900\n"
   .....:     "KORD,19990127, 23:00:00, 22:56:00, -0.5900"
   .....: )
   .....:

In [109]: with open("tmp.csv", "w") as fh:
   .....:     fh.write(data)
   .....:

In [110]: df = pd.read_csv("tmp.csv", header=None, parse_dates=[[1, 2], [1, 3]])

In [111]: df
Out[111]:
                  1_2                 1_3     0     4
0 1999-01-27 19:00:00 1999-01-27 18:56:00  KORD  0.81
1 1999-01-27 20:00:00 1999-01-27 19:56:00  KORD  0.01
2 1999-01-27 21:00:00 1999-01-27 20:56:00  KORD -0.59
3 1999-01-27 21:00:00 1999-01-27 21:18:00  KORD -0.99
4 1999-01-27 22:00:00 1999-01-27 21:56:00  KORD -0.59
5 1999-01-27 23:00:00 1999-01-27 22:56:00  KORD -0.59

In [112]: df = pd.read_csv(
   .....:     "tmp.csv", header=None, parse_dates=[[1, 2], [1, 3]], keep_date_col=True
   .....: )
   .....:

In [113]: df
Out[113]:
                  1_2                 1_3     0  ...          2          3     4
0 1999-01-27 19:00:00 1999-01-27 18:56:00  KORD  ...   19:00:00   18:56:00  0.81
1 1999-01-27 20:00:00 1999-01-27 19:56:00  KORD  ...   20:00:00   19:56:00  0.01
2 1999-01-27 21:00:00 1999-01-27 20:56:00  KORD  ...   21:00:00   20:56:00 -0.59
3 1999-01-27 21:00:00 1999-01-27 21:18:00  KORD  ...   21:00:00   21:18:00 -0.99
4 1999-01-27 22:00:00 1999-01-27 21:56:00  KORD  ...   22:00:00   21:56:00 -0.59
5 1999-01-27 23:00:00 1999-01-27 22:56:00  KORD  ...   23:00:00   22:56:00 -0.59

[6 rows x 7 columns]

In [114]: date_spec = {"nominal": [1, 2], "actual": [1, 3]}

In [115]: df = pd.read_csv("tmp.csv", header=None, parse_dates=date_spec)

In [116]: df
Out[116]:
              nominal              actual     0     4
0 1999-01-27 19:00:00 1999-01-27 18:56:00  KORD  0.81
1 1999-01-27 20:00:00 1999-01-27 19:56:00  KORD  0.01
2 1999-01-27 21:00:00 1999-01-27 20:56:00  KORD -0.59
3 1999-01-27 21:00:00 1999-01-27 21:18:00  KORD -0.99
4 1999-01-27 22:00:00 1999-01-27 21:56:00  KORD -0.59
5 1999-01-27 23:00:00 1999-01-27 22:56:00  KORD -0.59

In [117]: date_spec = {"nominal": [1, 2], "actual": [1, 3]}

In [118]: df = pd.read_csv(
   .....:     "tmp.csv", header=None, parse_dates=date_spec, index_col=0
   .....: )  # index is the nominal column
   .....:

In [119]: df
Out[119]:
                                 actual     0     4
nominal
1999-01-27 19:00:00 1999-01-27 18:56:00  KORD  0.81
1999-01-27 20:00:00 1999-01-27 19:56:00  KORD  0.01
1999-01-27 21:00:00 1999-01-27 20:56:00  KORD -0.59
1999-01-27 21:00:00 1999-01-27 21:18:00  KORD -0.99
1999-01-27 22:00:00 1999-01-27 21:56:00  KORD -0.59
1999-01-27 23:00:00 1999-01-27 22:56:00  KORD -0.59

In [120]: content = """\
   .....: a
   .....: 2000-01-01T00:00:00+05:00
   .....: 2000-01-01T00:00:00+06:00"""
   .....:

In [121]: df = pd.read_csv(StringIO(content))

In [122]: df["a"] = pd.to_datetime(df["a"], utc=True)

In [123]: df["a"]
Out[123]:
0   1999-12-31 19:00:00+00:00
1   1999-12-31 18:00:00+00:00
Name: a, dtype: datetime64[ns, UTC]

In [124]: df = pd.read_csv(
   .....:     "foo.csv",
   .....:     index_col=0,
   .....:     parse_dates=True,
   .....: )
   .....:

In [125]: df
Out[125]:
            A  B  C
date
2009-01-01  a  1  2
2009-01-02  b  3  4
2009-01-03  c  4  5

In [126]: data = StringIO("date\n12 Jan 2000\n2000-01-13\n")

In [127]: df = pd.read_csv(data)

In [128]: df['date'] = pd.to_datetime(df['date'], format='mixed')

In [129]: df
Out[129]:
        date
0 2000-01-12
1 2000-01-13

In [130]: data = StringIO("date\n2020-01-01\n2020-01-01 03:00\n")

In [131]: df = pd.read_csv(data)

In [132]: df['date'] = pd.to_datetime(df['date'], format='ISO8601')

In [133]: df
Out[133]:
                 date
0 2020-01-01 00:00:00
1 2020-01-01 03:00:00

In [134]: data = "date,value,cat\n1/6/2000,5,a\n2/6/2000,10,b\n3/6/2000,15,c"

In [135]: print(data)
date,value,cat
1/6/2000,5,a
2/6/2000,10,b
3/6/2000,15,c

In [136]: with open("tmp.csv", "w") as fh:
   .....:     fh.write(data)
   .....:

In [137]: pd.read_csv("tmp.csv", parse_dates=[0])
Out[137]:
        date  value cat
0 2000-01-06      5   a
1 2000-02-06     10   b
2 2000-03-06     15   c

In [138]: pd.read_csv("tmp.csv", dayfirst=True, parse_dates=[0])
Out[138]:
        date  value cat
0 2000-06-01      5   a
1 2000-06-02     10   b
2 2000-06-03     15   c

In [139]: import io

In [140]: data = pd.DataFrame([0, 1, 2])

In [141]: buffer = io.BytesIO()

In [142]: data.to_csv(buffer, encoding="utf-8", compression="gzip")

In [143]: val = "0.3066101993807095471566981359501369297504425048828125"

In [144]: data = "a,b,c\n1,2,{0}".format(val)

In [145]: abs(
   .....:     pd.read_csv(
   .....:         StringIO(data),
   .....:         engine="c",
   .....:         float_precision=None,
   .....:     )["c"][0] - float(val)
   .....: )
   .....:
Out[145]: 5.551115123125783e-17

In [146]: abs(
   .....:     pd.read_csv(
   .....:         StringIO(data),
   .....:         engine="c",
   .....:         float_precision="high",
   .....:     )["c"][0] - float(val)
   .....: )
   .....:
Out[146]: 5.551115123125783e-17

In [147]: abs(
   .....:     pd.read_csv(StringIO(data), engine="c", float_precision="round_trip")["c"][0]
   .....:     - float(val)
   .....: )
   .....:
Out[147]: 0.0

In [148]: data = (
   .....:     "ID|level|category\n"
   .....:     "Patient1|123,000|x\n"
   .....:     "Patient2|23,000|y\n"
   .....:     "Patient3|1,234,018|z"
   .....: )
   .....:

In [149]: with open("tmp.csv", "w") as fh:
   .....:     fh.write(data)
   .....:

In [150]: df = pd.read_csv("tmp.csv", sep="|")

In [151]: df
Out[151]:
         ID      level category
0  Patient1    123,000        x
1  Patient2     23,000        y
2  Patient3  1,234,018        z

In [152]: df.level.dtype
Out[152]: dtype('O')

In [153]: df = pd.read_csv("tmp.csv", sep="|", thousands=",")

In [154]: df
Out[154]:
         ID    level category
0  Patient1   123000        x
1  Patient2    23000        y
2  Patient3  1234018        z

In [155]: df.level.dtype
Out[155]: dtype('int64')

pd.read_csv("path_to_file.csv", na_values=[5])

pd.read_csv("path_to_file.csv", keep_default_na=False, na_values=[""])

pd.read_csv("path_to_file.csv", keep_default_na=False, na_values=["NA", "0"])

pd.read_csv("path_to_file.csv", na_values=["Nope"])

In [156]: data = "a,b,c\n1,Yes,2\n3,No,4"

In [157]: print(data)
a,b,c
1,Yes,2
3,No,4

In [158]: pd.read_csv(StringIO(data))
Out[158]:
   a    b  c
0  1  Yes  2
1  3   No  4

In [159]: pd.read_csv(StringIO(data), true_values=["Yes"], false_values=["No"])
Out[159]:
   a      b  c
0  1   True  2
1  3  False  4

In [160]: data = "a,b,c\n1,2,3\n4,5,6,7\n8,9,10"

In [161]: pd.read_csv(StringIO(data))
---------------------------------------------------------------------------
ParserError                               Traceback (most recent call last)
Cell In[161], line 1
----> 1 pd.read_csv(StringIO(data))

File ~/work/pandas/pandas/pandas/io/parsers/readers.py:1026, in read_csv(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)
   1013 kwds_defaults = _refine_defaults_read(
   1014     dialect,
   1015     delimiter,
   (...)
   1022     dtype_backend=dtype_backend,
   1023 )
   1024 kwds.update(kwds_defaults)
-> 1026 return _read(filepath_or_buffer, kwds)

File ~/work/pandas/pandas/pandas/io/parsers/readers.py:626, in _read(filepath_or_buffer, kwds)
    623     return parser
    625 with parser:
--> 626     return parser.read(nrows)

File ~/work/pandas/pandas/pandas/io/parsers/readers.py:1923, in TextFileReader.read(self, nrows)
   1916 nrows = validate_integer("nrows", nrows)
   1917 try:
   1918     # error: "ParserBase" has no attribute "read"
   1919     (
   1920         index,
   1921         columns,
   1922         col_dict,
-> 1923     ) = self._engine.read(  # type: ignore[attr-defined]
   1924         nrows
   1925     )
   1926 except Exception:
   1927     self.close()

File ~/work/pandas/pandas/pandas/io/parsers/c_parser_wrapper.py:234, in CParserWrapper.read(self, nrows)
    232 try:
    233     if self.low_memory:
--> 234         chunks = self._reader.read_low_memory(nrows)
    235         # destructive to chunks
    236         data = _concatenate_chunks(chunks)

File parsers.pyx:838, in pandas._libs.parsers.TextReader.read_low_memory()

File parsers.pyx:905, in pandas._libs.parsers.TextReader._read_rows()

File parsers.pyx:874, in pandas._libs.parsers.TextReader._tokenize_rows()

File parsers.pyx:891, in pandas._libs.parsers.TextReader._check_tokenize_status()

File parsers.pyx:2061, in pandas._libs.parsers.raise_parser_error()

ParserError: Error tokenizing data. C error: Expected 3 fields in line 3, saw 4

In [162]: data = "a,b,c\n1,2,3\n4,5,6,7\n8,9,10"

In [163]: pd.read_csv(StringIO(data), on_bad_lines="skip")
Out[163]:
   a  b   c
0  1  2   3
1  8  9  10

In [164]: external_list = []

In [165]: def bad_lines_func(line):
   .....:     external_list.append(line)
   .....:     return line[-3:]
   .....:

In [166]: external_list
Out[166]: []

In [167]: bad_lines_func = lambda line: print(line)

In [168]: data = 'name,type\nname a,a is of type a\nname b,"b\" is of type b"'

In [169]: data
Out[169]: 'name,type\nname a,a is of type a\nname b,"b" is of type b"'

In [170]: pd.read_csv(StringIO(data), on_bad_lines=bad_lines_func, engine="python")
Out[170]:
     name            type
0  name a  a is of type a

In [171]: pd.read_csv(StringIO(data), usecols=[0, 1, 2])
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
Cell In[171], line 1
----> 1 pd.read_csv(StringIO(data), usecols=[0, 1, 2])

File ~/work/pandas/pandas/pandas/io/parsers/readers.py:1026, in read_csv(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)
   1013 kwds_defaults = _refine_defaults_read(
   1014     dialect,
   1015     delimiter,
   (...)
   1022     dtype_backend=dtype_backend,
   1023 )
   1024 kwds.update(kwds_defaults)
-> 1026 return _read(filepath_or_buffer, kwds)

File ~/work/pandas/pandas/pandas/io/parsers/readers.py:620, in _read(filepath_or_buffer, kwds)
    617 _validate_names(kwds.get("names", None))
    619 # Create the parser.
--> 620 parser = TextFileReader(filepath_or_buffer, **kwds)
    622 if chunksize or iterator:
    623     return parser

File ~/work/pandas/pandas/pandas/io/parsers/readers.py:1620, in TextFileReader.__init__(self, f, engine, **kwds)
   1617     self.options["has_index_names"] = kwds["has_index_names"]
   1619 self.handles: IOHandles | None = None
-> 1620 self._engine = self._make_engine(f, self.engine)

File ~/work/pandas/pandas/pandas/io/parsers/readers.py:1898, in TextFileReader._make_engine(self, f, engine)
   1895     raise ValueError(msg)
   1897 try:
-> 1898     return mapping[engine](f, **self.options)
   1899 except Exception:
   1900     if self.handles is not None:

File ~/work/pandas/pandas/pandas/io/parsers/c_parser_wrapper.py:155, in CParserWrapper.__init__(self, src, **kwds)
    152     # error: Cannot determine type of 'names'
    153     if len(self.names) < len(usecols):  # type: ignore[has-type]
    154         # error: Cannot determine type of 'names'
--> 155         self._validate_usecols_names(
    156             usecols,
    157             self.names,  # type: ignore[has-type]
    158         )
    160 # error: Cannot determine type of 'names'
    161 self._validate_parse_dates_presence(self.names)  # type: ignore[has-type]

File ~/work/pandas/pandas/pandas/io/parsers/base_parser.py:979, in ParserBase._validate_usecols_names(self, usecols, names)
    977 missing = [c for c in usecols if c not in names]
    978 if len(missing) > 0:
--> 979     raise ValueError(
    980         f"Usecols do not match columns, columns expected but not found: "
    981         f"{missing}"
    982     )
    984 return usecols

ValueError: Usecols do not match columns, columns expected but not found: [0, 1, 2]

In [172]: pd.read_csv(StringIO(data), names=['a', 'b', 'c', 'd'])
Out[172]:
        a                b   c   d
0    name             type NaN NaN
1  name a   a is of type a NaN NaN
2  name b  b is of type b" NaN NaN

In [173]: data = "label1,label2,label3\n" 'index1,"a,c,e\n' "index2,b,d,f"

In [174]: print(data)
label1,label2,label3
index1,"a,c,e
index2,b,d,f

In [175]: import csv

In [176]: dia = csv.excel()

In [177]: dia.quoting = csv.QUOTE_NONE

In [178]: pd.read_csv(StringIO(data), dialect=dia)
Out[178]:
       label1 label2 label3
index1     "a      c      e
index2      b      d      f

In [179]: data = "a,b,c~1,2,3~4,5,6"

In [180]: pd.read_csv(StringIO(data), lineterminator="~")
Out[180]:
   a  b  c
0  1  2  3
1  4  5  6

In [181]: data = "a, b, c\n1, 2, 3\n4, 5, 6"

In [182]: print(data)
a, b, c
1, 2, 3
4, 5, 6

In [183]: pd.read_csv(StringIO(data), skipinitialspace=True)
Out[183]:
   a  b  c
0  1  2  3
1  4  5  6

In [184]: data = 'a,b\n"hello, \\"Bob\\", nice to see you",5'

In [185]: print(data)
a,b
"hello, \"Bob\", nice to see you",5

In [186]: pd.read_csv(StringIO(data), escapechar="\\")
Out[186]:
                               a  b
0  hello, "Bob", nice to see you  5

In [187]: data1 = (
   .....:     "id8141    360.242940   149.910199   11950.7\n"
   .....:     "id1594    444.953632   166.985655   11788.4\n"
   .....:     "id1849    364.136849   183.628767   11806.2\n"
   .....:     "id1230    413.836124   184.375703   11916.8\n"
   .....:     "id1948    502.953953   173.237159   12468.3"
   .....: )
   .....:

In [188]: with open("bar.csv", "w") as f:
   .....:     f.write(data1)
   .....:

# Column specifications are a list of half-intervals
In [189]: colspecs = [(0, 6), (8, 20), (21, 33), (34, 43)]

In [190]: df = pd.read_fwf("bar.csv", colspecs=colspecs, header=None, index_col=0)

In [191]: df
Out[191]:
                 1           2        3
0
id8141  360.242940  149.910199  11950.7
id1594  444.953632  166.985655  11788.4
id1849  364.136849  183.628767  11806.2
id1230  413.836124  184.375703  11916.8
id1948  502.953953  173.237159  12468.3

# Widths are a list of integers
In [192]: widths = [6, 14, 13, 10]

In [193]: df = pd.read_fwf("bar.csv", widths=widths, header=None)

In [194]: df
Out[194]:
        0           1           2        3
0  id8141  360.242940  149.910199  11950.7
1  id1594  444.953632  166.985655  11788.4
2  id1849  364.136849  183.628767  11806.2
3  id1230  413.836124  184.375703  11916.8
4  id1948  502.953953  173.237159  12468.3

In [195]: df = pd.read_fwf("bar.csv", header=None, index_col=0)

In [196]: df
Out[196]:
                 1           2        3
0
id8141  360.242940  149.910199  11950.7
id1594  444.953632  166.985655  11788.4
id1849  364.136849  183.628767  11806.2
id1230  413.836124  184.375703  11916.8
id1948  502.953953  173.237159  12468.3

In [197]: pd.read_fwf("bar.csv", header=None, index_col=0).dtypes
Out[197]:
1    float64
2    float64
3    float64
dtype: object

In [198]: pd.read_fwf("bar.csv", header=None, dtype={2: "object"}).dtypes
Out[198]:
0     object
1    float64
2     object
3    float64
dtype: object

In [199]: data = "A,B,C\n20090101,a,1,2\n20090102,b,3,4\n20090103,c,4,5"

In [200]: print(data)
A,B,C
20090101,a,1,2
20090102,b,3,4
20090103,c,4,5

In [201]: with open("foo.csv", "w") as f:
   .....:     f.write(data)
   .....:

In [202]: pd.read_csv("foo.csv")
Out[202]:
          A  B  C
20090101  a  1  2
20090102  b  3  4
20090103  c  4  5

In [203]: df = pd.read_csv("foo.csv", parse_dates=True)

In [204]: df.index
Out[204]: DatetimeIndex(['2009-01-01', '2009-01-02', '2009-01-03'], dtype='datetime64[ns]', freq=None)

In [205]: data = 'year,indiv,zit,xit\n1977,"A",1.2,.6\n1977,"B",1.5,.5'

In [206]: print(data)
year,indiv,zit,xit
1977,"A",1.2,.6
1977,"B",1.5,.5

In [207]: with open("mindex_ex.csv", mode="w") as f:
   .....:     f.write(data)
   .....:

In [208]: df = pd.read_csv("mindex_ex.csv", index_col=[0, 1])

In [209]: df
Out[209]:
            zit  xit
year indiv
1977 A      1.2  0.6
     B      1.5  0.5

In [210]: df.loc[1977]
Out[210]:
       zit  xit
indiv
A      1.2  0.6
B      1.5  0.5

In [211]: mi_idx = pd.MultiIndex.from_arrays([[1, 2, 3, 4], list("abcd")], names=list("ab"))

In [212]: mi_col = pd.MultiIndex.from_arrays([[1, 2], list("ab")], names=list("cd"))

In [213]: df = pd.DataFrame(np.ones((4, 2)), index=mi_idx, columns=mi_col)

In [214]: df.to_csv("mi.csv")

In [215]: print(open("mi.csv").read())
c,,1,2
d,,a,b
a,b,,
1,a,1.0,1.0
2,b,1.0,1.0
3,c,1.0,1.0
4,d,1.0,1.0


In [216]: pd.read_csv("mi.csv", header=[0, 1, 2, 3], index_col=[0, 1])
Out[216]:
c                    1                  2
d                    a                  b
a   Unnamed: 2_level_2 Unnamed: 3_level_2
1                  1.0                1.0
2 b                1.0                1.0
3 c                1.0                1.0
4 d                1.0                1.0

In [217]: data = ",a,a,a,b,c,c\n,q,r,s,t,u,v\none,1,2,3,4,5,6\ntwo,7,8,9,10,11,12"

In [218]: print(data)
,a,a,a,b,c,c
,q,r,s,t,u,v
one,1,2,3,4,5,6
two,7,8,9,10,11,12

In [219]: with open("mi2.csv", "w") as fh:
   .....:     fh.write(data)
   .....:

In [220]: pd.read_csv("mi2.csv", header=[0, 1], index_col=0)
Out[220]:
     a         b   c
     q  r  s   t   u   v
one  1  2  3   4   5   6
two  7  8  9  10  11  12

In [221]: df = pd.DataFrame(np.random.randn(10, 4))

In [222]: df.to_csv("tmp2.csv", sep=":", index=False)

In [223]: pd.read_csv("tmp2.csv", sep=None, engine="python")
Out[223]:
          0         1         2         3
0  0.469112 -0.282863 -1.509059 -1.135632
1  1.212112 -0.173215  0.119209 -1.044236
2 -0.861849 -2.104569 -0.494929  1.071804
3  0.721555 -0.706771 -1.039575  0.271860
4 -0.424972  0.567020  0.276232 -1.087401
5 -0.673690  0.113648 -1.478427  0.524988
6  0.404705  0.577046 -1.715002 -1.039268
7 -0.370647 -1.157892 -1.344312  0.844885
8  1.075770 -0.109050  1.643563 -1.469388
9  0.357021 -0.674600 -1.776904 -0.968914

In [224]: df = pd.DataFrame(np.random.randn(10, 4))

In [225]: df.to_csv("tmp.csv", index=False)

In [226]: table = pd.read_csv("tmp.csv")

In [227]: table
Out[227]:
          0         1         2         3
0 -1.294524  0.413738  0.276662 -0.472035
1 -0.013960 -0.362543 -0.006154 -0.923061
2  0.895717  0.805244 -1.206412  2.565646
3  1.431256  1.340309 -1.170299 -0.226169
4  0.410835  0.813850  0.132003 -0.827317
5 -0.076467 -1.187678  1.130127 -1.436737
6 -1.413681  1.607920  1.024180  0.569605
7  0.875906 -2.211372  0.974466 -2.006747
8 -0.410001 -0.078638  0.545952 -1.219217
9 -1.226825  0.769804 -1.281247 -0.727707

In [228]: with pd.read_csv("tmp.csv", chunksize=4) as reader:
   .....:     print(reader)
   .....:     for chunk in reader:
   .....:         print(chunk)
   .....:
<pandas.io.parsers.readers.TextFileReader object at 0x7ff2e5421db0>
          0         1         2         3
0 -1.294524  0.413738  0.276662 -0.472035
1 -0.013960 -0.362543 -0.006154 -0.923061
2  0.895717  0.805244 -1.206412  2.565646
3  1.431256  1.340309 -1.170299 -0.226169
          0         1         2         3
4  0.410835  0.813850  0.132003 -0.827317
5 -0.076467 -1.187678  1.130127 -1.436737
6 -1.413681  1.607920  1.024180  0.569605
7  0.875906 -2.211372  0.974466 -2.006747
          0         1         2         3
8 -0.410001 -0.078638  0.545952 -1.219217
9 -1.226825  0.769804 -1.281247 -0.727707

In [229]: with pd.read_csv("tmp.csv", iterator=True) as reader:
   .....:     print(reader.get_chunk(5))
   .....:
          0         1         2         3
0 -1.294524  0.413738  0.276662 -0.472035
1 -0.013960 -0.362543 -0.006154 -0.923061
2  0.895717  0.805244 -1.206412  2.565646
3  1.431256  1.340309 -1.170299 -0.226169
4  0.410835  0.813850  0.132003 -0.827317

df = pd.read_csv("https://download.bls.gov/pub/time.series/cu/cu.item", sep="\t")

headers = {"User-Agent": "pandas"}
df = pd.read_csv(
    "https://download.bls.gov/pub/time.series/cu/cu.item",
    sep="\t",
    storage_options=headers
)

df = pd.read_json("s3://pandas-test/adatafile.json")

storage_options = {"client_kwargs": {"endpoint_url": "http://127.0.0.1:5555"}}}
df = pd.read_json("s3://pandas-test/test-1", storage_options=storage_options)

pd.read_csv(
    "s3://ncei-wcsd-archive/data/processed/SH1305/18kHz/SaKe2013"
    "-D20130523-T080854_to_SaKe2013-D20130523-T085643.csv",
    storage_options={"anon": True},
)

pd.read_csv(
    "simplecache::s3://ncei-wcsd-archive/data/processed/SH1305/18kHz/"
    "SaKe2013-D20130523-T080854_to_SaKe2013-D20130523-T085643.csv",
    storage_options={"s3": {"anon": True}},
)

In [230]: dfj = pd.DataFrame(np.random.randn(5, 2), columns=list("AB"))

In [231]: json = dfj.to_json()

In [232]: json
Out[232]: '{"A":{"0":-0.1213062281,"1":0.6957746499,"2":0.9597255933,"3":-0.6199759194,"4":-0.7323393705},"B":{"0":-0.0978826728,"1":0.3417343559,"2":-1.1103361029,"3":0.1497483186,"4":0.6877383895}}'

In [233]: dfjo = pd.DataFrame(
   .....:     dict(A=range(1, 4), B=range(4, 7), C=range(7, 10)),
   .....:     columns=list("ABC"),
   .....:     index=list("xyz"),
   .....: )
   .....:

In [234]: dfjo
Out[234]:
   A  B  C
x  1  4  7
y  2  5  8
z  3  6  9

In [235]: sjo = pd.Series(dict(x=15, y=16, z=17), name="D")

In [236]: sjo
Out[236]:
x    15
y    16
z    17
Name: D, dtype: int64

In [237]: dfjo.to_json(orient="columns")
Out[237]: '{"A":{"x":1,"y":2,"z":3},"B":{"x":4,"y":5,"z":6},"C":{"x":7,"y":8,"z":9}}'

# Not available for Series

In [238]: dfjo.to_json(orient="index")
Out[238]: '{"x":{"A":1,"B":4,"C":7},"y":{"A":2,"B":5,"C":8},"z":{"A":3,"B":6,"C":9}}'

In [239]: sjo.to_json(orient="index")
Out[239]: '{"x":15,"y":16,"z":17}'

In [240]: dfjo.to_json(orient="records")
Out[240]: '[{"A":1,"B":4,"C":7},{"A":2,"B":5,"C":8},{"A":3,"B":6,"C":9}]'

In [241]: sjo.to_json(orient="records")
Out[241]: '[15,16,17]'

In [242]: dfjo.to_json(orient="values")
Out[242]: '[[1,4,7],[2,5,8],[3,6,9]]'

# Not available for Series

In [243]: dfjo.to_json(orient="split")
Out[243]: '{"columns":["A","B","C"],"index":["x","y","z"],"data":[[1,4,7],[2,5,8],[3,6,9]]}'

In [244]: sjo.to_json(orient="split")
Out[244]: '{"name":"D","index":["x","y","z"],"data":[15,16,17]}'

In [245]: dfd = pd.DataFrame(np.random.randn(5, 2), columns=list("AB"))

In [246]: dfd["date"] = pd.Timestamp("20130101")

In [247]: dfd = dfd.sort_index(axis=1, ascending=False)

In [248]: json = dfd.to_json(date_format="iso")

In [249]: json
Out[249]: '{"date":{"0":"2013-01-01T00:00:00.000","1":"2013-01-01T00:00:00.000","2":"2013-01-01T00:00:00.000","3":"2013-01-01T00:00:00.000","4":"2013-01-01T00:00:00.000"},"B":{"0":0.403309524,"1":0.3016244523,"2":-1.3698493577,"3":1.4626960492,"4":-0.8265909164},"A":{"0":0.1764443426,"1":-0.1549507744,"2":-2.1798606054,"3":-0.9542078401,"4":-1.7431609117}}'

In [250]: json = dfd.to_json(date_format="iso", date_unit="us")

In [251]: json
Out[251]: '{"date":{"0":"2013-01-01T00:00:00.000000","1":"2013-01-01T00:00:00.000000","2":"2013-01-01T00:00:00.000000","3":"2013-01-01T00:00:00.000000","4":"2013-01-01T00:00:00.000000"},"B":{"0":0.403309524,"1":0.3016244523,"2":-1.3698493577,"3":1.4626960492,"4":-0.8265909164},"A":{"0":0.1764443426,"1":-0.1549507744,"2":-2.1798606054,"3":-0.9542078401,"4":-1.7431609117}}'

In [252]: json = dfd.to_json(date_format="epoch", date_unit="s")

In [253]: json
Out[253]: '{"date":{"0":1,"1":1,"2":1,"3":1,"4":1},"B":{"0":0.403309524,"1":0.3016244523,"2":-1.3698493577,"3":1.4626960492,"4":-0.8265909164},"A":{"0":0.1764443426,"1":-0.1549507744,"2":-2.1798606054,"3":-0.9542078401,"4":-1.7431609117}}'

In [254]: dfj2 = dfj.copy()

In [255]: dfj2["date"] = pd.Timestamp("20130101")

In [256]: dfj2["ints"] = list(range(5))

In [257]: dfj2["bools"] = True

In [258]: dfj2.index = pd.date_range("20130101", periods=5)

In [259]: dfj2.to_json("test.json")

In [260]: with open("test.json") as fh:
   .....:     print(fh.read())
   .....:
{"A":{"1356998400000":-0.1213062281,"1357084800000":0.6957746499,"1357171200000":0.9597255933,"1357257600000":-0.6199759194,"1357344000000":-0.7323393705},"B":{"1356998400000":-0.0978826728,"1357084800000":0.3417343559,"1357171200000":-1.1103361029,"1357257600000":0.1497483186,"1357344000000":0.6877383895},"date":{"1356998400000":1356,"1357084800000":1356,"1357171200000":1356,"1357257600000":1356,"1357344000000":1356},"ints":{"1356998400000":0,"1357084800000":1,"1357171200000":2,"1357257600000":3,"1357344000000":4},"bools":{"1356998400000":true,"1357084800000":true,"1357171200000":true,"1357257600000":true,"1357344000000":true}}

>>> DataFrame([1.0, 2.0, complex(1.0, 2.0)]).to_json()  # raises
RuntimeError: Unhandled numpy dtype 15

In [261]: pd.DataFrame([1.0, 2.0, complex(1.0, 2.0)]).to_json(default_handler=str)
Out[261]: '{"0":{"0":"(1+0j)","1":"(2+0j)","2":"(1+2j)"}}'

In [262]: from io import StringIO

In [263]: pd.read_json(StringIO(json))
Out[263]:
   date         B         A
0     1  0.403310  0.176444
1     1  0.301624 -0.154951
2     1 -1.369849 -2.179861
3     1  1.462696 -0.954208
4     1 -0.826591 -1.743161

In [264]: pd.read_json("test.json")
Out[264]:
                   A         B  date  ints  bools
2013-01-01 -0.121306 -0.097883  1356     0   True
2013-01-02  0.695775  0.341734  1356     1   True
2013-01-03  0.959726 -1.110336  1356     2   True
2013-01-04 -0.619976  0.149748  1356     3   True
2013-01-05 -0.732339  0.687738  1356     4   True

In [265]: pd.read_json("test.json", dtype=object).dtypes
Out[265]:
A        object
B        object
date     object
ints     object
bools    object
dtype: object

In [266]: pd.read_json("test.json", dtype={"A": "float32", "bools": "int8"}).dtypes
Out[266]:
A        float32
B        float64
date       int64
ints       int64
bools       int8
dtype: object

In [267]: from io import StringIO

In [268]: si = pd.DataFrame(
   .....:     np.zeros((4, 4)), columns=list(range(4)), index=[str(i) for i in range(4)]
   .....: )
   .....:

In [269]: si
Out[269]:
     0    1    2    3
0  0.0  0.0  0.0  0.0
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
3  0.0  0.0  0.0  0.0

In [270]: si.index
Out[270]: Index(['0', '1', '2', '3'], dtype='object')

In [271]: si.columns
Out[271]: Index([0, 1, 2, 3], dtype='int64')

In [272]: json = si.to_json()

In [273]: sij = pd.read_json(StringIO(json), convert_axes=False)

In [274]: sij
Out[274]:
   0  1  2  3
0  0  0  0  0
1  0  0  0  0
2  0  0  0  0
3  0  0  0  0

In [275]: sij.index
Out[275]: Index(['0', '1', '2', '3'], dtype='object')

In [276]: sij.columns
Out[276]: Index(['0', '1', '2', '3'], dtype='object')

In [277]: from io import StringIO

In [278]: json = dfj2.to_json(date_unit="ns")

# Try to parse timestamps as milliseconds -> Won't Work
In [279]: dfju = pd.read_json(StringIO(json), date_unit="ms")

In [280]: dfju
Out[280]:
                            A         B        date  ints  bools
1356998400000000000 -0.121306 -0.097883  1356998400     0   True
1357084800000000000  0.695775  0.341734  1356998400     1   True
1357171200000000000  0.959726 -1.110336  1356998400     2   True
1357257600000000000 -0.619976  0.149748  1356998400     3   True
1357344000000000000 -0.732339  0.687738  1356998400     4   True

# Let pandas detect the correct precision
In [281]: dfju = pd.read_json(StringIO(json))

In [282]: dfju
Out[282]:
                   A         B       date  ints  bools
2013-01-01 -0.121306 -0.097883 2013-01-01     0   True
2013-01-02  0.695775  0.341734 2013-01-01     1   True
2013-01-03  0.959726 -1.110336 2013-01-01     2   True
2013-01-04 -0.619976  0.149748 2013-01-01     3   True
2013-01-05 -0.732339  0.687738 2013-01-01     4   True

# Or specify that all timestamps are in nanoseconds
In [283]: dfju = pd.read_json(StringIO(json), date_unit="ns")

In [284]: dfju
Out[284]:
                   A         B        date  ints  bools
2013-01-01 -0.121306 -0.097883  1356998400     0   True
2013-01-02  0.695775  0.341734  1356998400     1   True
2013-01-03  0.959726 -1.110336  1356998400     2   True
2013-01-04 -0.619976  0.149748  1356998400     3   True
2013-01-05 -0.732339  0.687738  1356998400     4   True

In [285]: data = (
   .....:  '{"a":{"0":1,"1":3},"b":{"0":2.5,"1":4.5},"c":{"0":true,"1":false},"d":{"0":"a","1":"b"},'
   .....:  '"e":{"0":null,"1":6.0},"f":{"0":null,"1":7.5},"g":{"0":null,"1":true},"h":{"0":null,"1":"a"},'
   .....:  '"i":{"0":"12-31-2019","1":"12-31-2019"},"j":{"0":null,"1":null}}'
   .....: )
   .....:

In [286]: df = pd.read_json(StringIO(data), dtype_backend="pyarrow")

In [287]: df
Out[287]:
   a    b      c  d     e     f     g     h           i     j
0  1  2.5   True  a  <NA>  <NA>  <NA>  <NA>  12-31-2019  None
1  3  4.5  False  b     6   7.5  True     a  12-31-2019  None

In [288]: df.dtypes
Out[288]:
a     int64[pyarrow]
b    double[pyarrow]
c      bool[pyarrow]
d    string[pyarrow]
e     int64[pyarrow]
f    double[pyarrow]
g      bool[pyarrow]
h    string[pyarrow]
i    string[pyarrow]
j      null[pyarrow]
dtype: object

In [289]: data = [
   .....:     {"id": 1, "name": {"first": "Coleen", "last": "Volk"}},
   .....:     {"name": {"given": "Mark", "family": "Regner"}},
   .....:     {"id": 2, "name": "Faye Raker"},
   .....: ]
   .....:

In [290]: pd.json_normalize(data)
Out[290]:
    id name.first name.last name.given name.family        name
0  1.0     Coleen      Volk        NaN         NaN         NaN
1  NaN        NaN       NaN       Mark      Regner         NaN
2  2.0        NaN       NaN        NaN         NaN  Faye Raker

In [291]: data = [
   .....:     {
   .....:         "state": "Florida",
   .....:         "shortname": "FL",
   .....:         "info": {"governor": "Rick Scott"},
   .....:         "county": [
   .....:             {"name": "Dade", "population": 12345},
   .....:             {"name": "Broward", "population": 40000},
   .....:             {"name": "Palm Beach", "population": 60000},
   .....:         ],
   .....:     },
   .....:     {
   .....:         "state": "Ohio",
   .....:         "shortname": "OH",
   .....:         "info": {"governor": "John Kasich"},
   .....:         "county": [
   .....:             {"name": "Summit", "population": 1234},
   .....:             {"name": "Cuyahoga", "population": 1337},
   .....:         ],
   .....:     },
   .....: ]
   .....:

In [292]: pd.json_normalize(data, "county", ["state", "shortname", ["info", "governor"]])
Out[292]:
         name  population    state shortname info.governor
0        Dade       12345  Florida        FL    Rick Scott
1     Broward       40000  Florida        FL    Rick Scott
2  Palm Beach       60000  Florida        FL    Rick Scott
3      Summit        1234     Ohio        OH   John Kasich
4    Cuyahoga        1337     Ohio        OH   John Kasich

In [293]: data = [
   .....:     {
   .....:         "CreatedBy": {"Name": "User001"},
   .....:         "Lookup": {
   .....:             "TextField": "Some text",
   .....:             "UserField": {"Id": "ID001", "Name": "Name001"},
   .....:         },
   .....:         "Image": {"a": "b"},
   .....:     }
   .....: ]
   .....:

In [294]: pd.json_normalize(data, max_level=1)
Out[294]:
  CreatedBy.Name Lookup.TextField                    Lookup.UserField Image.a
0        User001        Some text  {'Id': 'ID001', 'Name': 'Name001'}       b

In [295]: from io import StringIO

In [296]: jsonl = """
   .....:     {"a": 1, "b": 2}
   .....:     {"a": 3, "b": 4}
   .....: """
   .....:

In [297]: df = pd.read_json(StringIO(jsonl), lines=True)

In [298]: df
Out[298]:
   a  b
0  1  2
1  3  4

In [299]: df.to_json(orient="records", lines=True)
Out[299]: '{"a":1,"b":2}\n{"a":3,"b":4}\n'

# reader is an iterator that returns ``chunksize`` lines each iteration
In [300]: with pd.read_json(StringIO(jsonl), lines=True, chunksize=1) as reader:
   .....:     reader
   .....:     for chunk in reader:
   .....:         print(chunk)
   .....:
Empty DataFrame
Columns: []
Index: []
   a  b
0  1  2
   a  b
1  3  4

In [301]: from io import BytesIO

In [302]: df = pd.read_json(BytesIO(jsonl.encode()), lines=True, engine="pyarrow")

In [303]: df
Out[303]:
   a  b
0  1  2
1  3  4

In [304]: df = pd.DataFrame(
   .....:     {
   .....:         "A": [1, 2, 3],
   .....:         "B": ["a", "b", "c"],
   .....:         "C": pd.date_range("2016-01-01", freq="d", periods=3),
   .....:     },
   .....:     index=pd.Index(range(3), name="idx"),
   .....: )
   .....:

In [305]: df
Out[305]:
     A  B          C
idx
0    1  a 2016-01-01
1    2  b 2016-01-02
2    3  c 2016-01-03

In [306]: df.to_json(orient="table", date_format="iso")
Out[306]: '{"schema":{"fields":[{"name":"idx","type":"integer"},{"name":"A","type":"integer"},{"name":"B","type":"string"},{"name":"C","type":"datetime"}],"primaryKey":["idx"],"pandas_version":"1.4.0"},"data":[{"idx":0,"A":1,"B":"a","C":"2016-01-01T00:00:00.000"},{"idx":1,"A":2,"B":"b","C":"2016-01-02T00:00:00.000"},{"idx":2,"A":3,"B":"c","C":"2016-01-03T00:00:00.000"}]}'

In [307]: from pandas.io.json import build_table_schema

In [308]: s = pd.Series(pd.date_range("2016", periods=4))

In [309]: build_table_schema(s)
Out[309]:
{'fields': [{'name': 'index', 'type': 'integer'},
  {'name': 'values', 'type': 'datetime'}],
 'primaryKey': ['index'],
 'pandas_version': '1.4.0'}

In [310]: s_tz = pd.Series(pd.date_range("2016", periods=12, tz="US/Central"))

In [311]: build_table_schema(s_tz)
Out[311]:
{'fields': [{'name': 'index', 'type': 'integer'},
  {'name': 'values', 'type': 'datetime', 'tz': 'US/Central'}],
 'primaryKey': ['index'],
 'pandas_version': '1.4.0'}

In [312]: s_per = pd.Series(1, index=pd.period_range("2016", freq="Y-DEC", periods=4))

In [313]: build_table_schema(s_per)
Out[313]:
{'fields': [{'name': 'index', 'type': 'datetime', 'freq': 'YE-DEC'},
  {'name': 'values', 'type': 'integer'}],
 'primaryKey': ['index'],
 'pandas_version': '1.4.0'}

In [314]: s_cat = pd.Series(pd.Categorical(["a", "b", "a"]))

In [315]: build_table_schema(s_cat)
Out[315]:
{'fields': [{'name': 'index', 'type': 'integer'},
  {'name': 'values',
   'type': 'any',
   'constraints': {'enum': ['a', 'b']},
   'ordered': False}],
 'primaryKey': ['index'],
 'pandas_version': '1.4.0'}

In [316]: s_dupe = pd.Series([1, 2], index=[1, 1])

In [317]: build_table_schema(s_dupe)
Out[317]:
{'fields': [{'name': 'index', 'type': 'integer'},
  {'name': 'values', 'type': 'integer'}],
 'pandas_version': '1.4.0'}

In [318]: s_multi = pd.Series(1, index=pd.MultiIndex.from_product([("a", "b"), (0, 1)]))

In [319]: build_table_schema(s_multi)
Out[319]:
{'fields': [{'name': 'level_0', 'type': 'string'},
  {'name': 'level_1', 'type': 'integer'},
  {'name': 'values', 'type': 'integer'}],
 'primaryKey': FrozenList(['level_0', 'level_1']),
 'pandas_version': '1.4.0'}

In [320]: df = pd.DataFrame(
   .....:     {
   .....:         "foo": [1, 2, 3, 4],
   .....:         "bar": ["a", "b", "c", "d"],
   .....:         "baz": pd.date_range("2018-01-01", freq="d", periods=4),
   .....:         "qux": pd.Categorical(["a", "b", "c", "c"]),
   .....:     },
   .....:     index=pd.Index(range(4), name="idx"),
   .....: )
   .....:

In [321]: df
Out[321]:
     foo bar        baz qux
idx
0      1   a 2018-01-01   a
1      2   b 2018-01-02   b
2      3   c 2018-01-03   c
3      4   d 2018-01-04   c

In [322]: df.dtypes
Out[322]:
foo             int64
bar            object
baz    datetime64[ns]
qux          category
dtype: object

In [323]: df.to_json("test.json", orient="table")

In [324]: new_df = pd.read_json("test.json", orient="table")

In [325]: new_df
Out[325]:
     foo bar        baz qux
idx
0      1   a 2018-01-01   a
1      2   b 2018-01-02   b
2      3   c 2018-01-03   c
3      4   d 2018-01-04   c

In [326]: new_df.dtypes
Out[326]:
foo             int64
bar            object
baz    datetime64[ns]
qux          category
dtype: object

In [327]: df.index.name = "index"

In [328]: df.to_json("test.json", orient="table")

In [329]: new_df = pd.read_json("test.json", orient="table")

In [330]: print(new_df.index.name)
None

In [320]: url = "https://www.fdic.gov/resources/resolutions/bank-failures/failed-bank-list"
In [321]: pd.read_html(url)
Out[321]:
[                         Bank NameBank           CityCity StateSt  ...              Acquiring InstitutionAI Closing DateClosing FundFund
 0                    Almena State Bank             Almena      KS  ...                          Equity Bank    October 23, 2020    10538
 1           First City Bank of Florida  Fort Walton Beach      FL  ...            United Fidelity Bank, fsb    October 16, 2020    10537
 2                 The First State Bank      Barboursville      WV  ...                       MVB Bank, Inc.       April 3, 2020    10536
 3                   Ericson State Bank            Ericson      NE  ...           Farmers and Merchants Bank   February 14, 2020    10535
 4     City National Bank of New Jersey             Newark      NJ  ...                      Industrial Bank    November 1, 2019    10534
 ..                                 ...                ...     ...  ...                                  ...                 ...      ...
 558                 Superior Bank, FSB           Hinsdale      IL  ...                Superior Federal, FSB       July 27, 2001     6004
 559                Malta National Bank              Malta      OH  ...                    North Valley Bank         May 3, 2001     4648
 560    First Alliance Bank & Trust Co.         Manchester      NH  ...  Southern New Hampshire Bank & Trust    February 2, 2001     4647
 561  National State Bank of Metropolis         Metropolis      IL  ...              Banterra Bank of Marion   December 14, 2000     4646
 562                   Bank of Honolulu           Honolulu      HI  ...                   Bank of the Orient    October 13, 2000     4645

 [563 rows x 7 columns]]

In [322]: url = 'https://www.sump.org/notes/request/' # HTTP request reflector
In [323]: pd.read_html(url)
Out[323]:
[                   0                    1
 0     Remote Socket:  51.15.105.256:51760
 1  Protocol Version:             HTTP/1.1
 2    Request Method:                  GET
 3       Request URI:      /notes/request/
 4     Request Query:                  NaN,
 0   Accept-Encoding:             identity
 1              Host:         www.sump.org
 2        User-Agent:    Python-urllib/3.8
 3        Connection:                close]
In [324]: headers = {
In [325]:    'User-Agent':'Mozilla Firefox v14.0',
In [326]:    'Accept':'application/json',
In [327]:    'Connection':'keep-alive',
In [328]:    'Auth':'Bearer 2*/f3+fe68df*4'
In [329]: }
In [340]: pd.read_html(url, storage_options=headers)
Out[340]:
[                   0                    1
 0     Remote Socket:  51.15.105.256:51760
 1  Protocol Version:             HTTP/1.1
 2    Request Method:                  GET
 3       Request URI:      /notes/request/
 4     Request Query:                  NaN,
 0        User-Agent: Mozilla Firefox v14.0
 1    AcceptEncoding:   gzip,  deflate,  br
 2            Accept:      application/json
 3        Connection:             keep-alive
 4              Auth:  Bearer 2*/f3+fe68df*4]

In [331]: html_str = """
   .....:          <table>
   .....:              <tr>
   .....:                  <th>A</th>
   .....:                  <th colspan="1">B</th>
   .....:                  <th rowspan="1">C</th>
   .....:              </tr>
   .....:              <tr>
   .....:                  <td>a</td>
   .....:                  <td>b</td>
   .....:                  <td>c</td>
   .....:              </tr>
   .....:          </table>
   .....:      """
   .....:

In [332]: with open("tmp.html", "w") as f:
   .....:     f.write(html_str)
   .....:

In [333]: df = pd.read_html("tmp.html")

In [334]: df[0]
Out[334]:
   A  B  C
0  a  b  c

In [335]: dfs = pd.read_html(StringIO(html_str))

In [336]: dfs[0]
Out[336]:
   A  B  C
0  a  b  c

match = "Metcalf Bank"
df_list = pd.read_html(url, match=match)

dfs = pd.read_html(url, header=0)

dfs = pd.read_html(url, index_col=0)

dfs = pd.read_html(url, skiprows=0)

dfs = pd.read_html(url, skiprows=range(2))

dfs1 = pd.read_html(url, attrs={"id": "table"})
dfs2 = pd.read_html(url, attrs={"class": "sortable"})
print(np.array_equal(dfs1[0], dfs2[0]))  # Should be True

dfs = pd.read_html(url, na_values=["No Acquirer"])

dfs = pd.read_html(url, keep_default_na=False)

url_mcc = "https://en.wikipedia.org/wiki/Mobile_country_code?oldid=899173761"
dfs = pd.read_html(
    url_mcc,
    match="Telekom Albania",
    header=0,
    converters={"MNC": str},
)

dfs = pd.read_html(url, match="Metcalf Bank", index_col=0)

df = pd.DataFrame(np.random.randn(2, 2))
s = df.to_html(float_format="{0:.40g}".format)
dfin = pd.read_html(s, index_col=0)

dfs = pd.read_html(url, "Metcalf Bank", index_col=0, flavor=["lxml"])

dfs = pd.read_html(url, "Metcalf Bank", index_col=0, flavor="lxml")

dfs = pd.read_html(url, "Metcalf Bank", index_col=0, flavor=["lxml", "bs4"])

In [337]: html_table = """
   .....: <table>
   .....:   <tr>
   .....:     <th>GitHub</th>
   .....:   </tr>
   .....:   <tr>
   .....:     <td><a href="https://github.com/pandas-dev/pandas">pandas</a></td>
   .....:   </tr>
   .....: </table>
   .....: """
   .....:

In [338]: df = pd.read_html(
   .....:     StringIO(html_table),
   .....:     extract_links="all"
   .....: )[0]
   .....:

In [339]: df
Out[339]:
                                   (GitHub, None)
0  (pandas, https://github.com/pandas-dev/pandas)

In [340]: df[("GitHub", None)]
Out[340]:
0    (pandas, https://github.com/pandas-dev/pandas)
Name: (GitHub, None), dtype: object

In [341]: df[("GitHub", None)].str[1]
Out[341]:
0    https://github.com/pandas-dev/pandas
Name: (GitHub, None), dtype: object

In [342]: from IPython.display import display, HTML

In [343]: df = pd.DataFrame(np.random.randn(2, 2))

In [344]: df
Out[344]:
          0         1
0 -0.345352  1.314232
1  0.690579  0.995761

In [345]: html = df.to_html()

In [346]: print(html)  # raw html
<table border="1" class="dataframe">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>0</th>
      <th>1</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <th>0</th>
      <td>-0.345352</td>
      <td>1.314232</td>
    </tr>
    <tr>
      <th>1</th>
      <td>0.690579</td>
      <td>0.995761</td>
    </tr>
  </tbody>
</table>

In [347]: display(HTML(html))
<IPython.core.display.HTML object>

In [348]: html = df.to_html(columns=[0])

In [349]: print(html)
<table border="1" class="dataframe">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>0</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <th>0</th>
      <td>-0.345352</td>
    </tr>
    <tr>
      <th>1</th>
      <td>0.690579</td>
    </tr>
  </tbody>
</table>

In [350]: display(HTML(html))
<IPython.core.display.HTML object>

In [351]: html = df.to_html(float_format="{0:.10f}".format)

In [352]: print(html)
<table border="1" class="dataframe">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>0</th>
      <th>1</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <th>0</th>
      <td>-0.3453521949</td>
      <td>1.3142323796</td>
    </tr>
    <tr>
      <th>1</th>
      <td>0.6905793352</td>
      <td>0.9957609037</td>
    </tr>
  </tbody>
</table>

In [353]: display(HTML(html))
<IPython.core.display.HTML object>

In [354]: html = df.to_html(bold_rows=False)

In [355]: print(html)
<table border="1" class="dataframe">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>0</th>
      <th>1</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <td>0</td>
      <td>-0.345352</td>
      <td>1.314232</td>
    </tr>
    <tr>
      <td>1</td>
      <td>0.690579</td>
      <td>0.995761</td>
    </tr>
  </tbody>
</table>

In [356]: display(HTML(html))
<IPython.core.display.HTML object>

In [357]: print(df.to_html(classes=["awesome_table_class", "even_more_awesome_class"]))
<table border="1" class="dataframe awesome_table_class even_more_awesome_class">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>0</th>
      <th>1</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <th>0</th>
      <td>-0.345352</td>
      <td>1.314232</td>
    </tr>
    <tr>
      <th>1</th>
      <td>0.690579</td>
      <td>0.995761</td>
    </tr>
  </tbody>
</table>

In [358]: url_df = pd.DataFrame(
   .....:     {
   .....:         "name": ["Python", "pandas"],
   .....:         "url": ["https://www.python.org/", "https://pandas.pydata.org"],
   .....:     }
   .....: )
   .....:

In [359]: html = url_df.to_html(render_links=True)

In [360]: print(html)
<table border="1" class="dataframe">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>name</th>
      <th>url</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <th>0</th>
      <td>Python</td>
      <td><a href="https://www.python.org/" target="_blank">https://www.python.org/</a></td>
    </tr>
    <tr>
      <th>1</th>
      <td>pandas</td>
      <td><a href="https://pandas.pydata.org" target="_blank">https://pandas.pydata.org</a></td>
    </tr>
  </tbody>
</table>

In [361]: display(HTML(html))
<IPython.core.display.HTML object>

In [362]: df = pd.DataFrame({"a": list("&<>"), "b": np.random.randn(3)})

In [363]: html = df.to_html()

In [364]: print(html)
<table border="1" class="dataframe">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>a</th>
      <th>b</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <th>0</th>
      <td>&amp;</td>
      <td>2.396780</td>
    </tr>
    <tr>
      <th>1</th>
      <td>&lt;</td>
      <td>0.014871</td>
    </tr>
    <tr>
      <th>2</th>
      <td>&gt;</td>
      <td>3.357427</td>
    </tr>
  </tbody>
</table>

In [365]: display(HTML(html))
<IPython.core.display.HTML object>

In [366]: html = df.to_html(escape=False)

In [367]: print(html)
<table border="1" class="dataframe">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>a</th>
      <th>b</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <th>0</th>
      <td>&</td>
      <td>2.396780</td>
    </tr>
    <tr>
      <th>1</th>
      <td><</td>
      <td>0.014871</td>
    </tr>
    <tr>
      <th>2</th>
      <td>></td>
      <td>3.357427</td>
    </tr>
  </tbody>
</table>

In [368]: display(HTML(html))
<IPython.core.display.HTML object>

In [369]: df = pd.DataFrame([[1, 2], [3, 4]], index=["a", "b"], columns=["c", "d"])

In [370]: print(df.style.to_latex())
\begin{tabular}{lrr}
 & c & d \\
a & 1 & 2 \\
b & 3 & 4 \\
\end{tabular}

In [371]: print(df.style.format("€ {}").to_latex())
\begin{tabular}{lrr}
 & c & d \\
a & € 1 & € 2 \\
b & € 3 & € 4 \\
\end{tabular}

In [372]: from io import StringIO

In [373]: xml = """<?xml version="1.0" encoding="UTF-8"?>
   .....: <bookstore>
   .....:   <book category="cooking">
   .....:     <title lang="en">Everyday Italian</title>
   .....:     <author>Giada De Laurentiis</author>
   .....:     <year>2005</year>
   .....:     <price>30.00</price>
   .....:   </book>
   .....:   <book category="children">
   .....:     <title lang="en">Harry Potter</title>
   .....:     <author>J K. Rowling</author>
   .....:     <year>2005</year>
   .....:     <price>29.99</price>
   .....:   </book>
   .....:   <book category="web">
   .....:     <title lang="en">Learning XML</title>
   .....:     <author>Erik T. Ray</author>
   .....:     <year>2003</year>
   .....:     <price>39.95</price>
   .....:   </book>
   .....: </bookstore>"""
   .....:

In [374]: df = pd.read_xml(StringIO(xml))

In [375]: df
Out[375]:
   category             title               author  year  price
0   cooking  Everyday Italian  Giada De Laurentiis  2005  30.00
1  children      Harry Potter         J K. Rowling  2005  29.99
2       web      Learning XML          Erik T. Ray  2003  39.95

In [376]: df = pd.read_xml("https://www.w3schools.com/xml/books.xml")

In [377]: df
Out[377]:
   category              title                  author  year  price      cover
0   cooking   Everyday Italian     Giada De Laurentiis  2005  30.00       None
1  children       Harry Potter            J K. Rowling  2005  29.99       None
2       web  XQuery Kick Start  Vaidyanathan Nagarajan  2003  49.99       None
3       web       Learning XML             Erik T. Ray  2003  39.95  paperback

In [378]: file_path = "books.xml"

In [379]: with open(file_path, "w") as f:
   .....:     f.write(xml)
   .....:

In [380]: with open(file_path, "r") as f:
   .....:     df = pd.read_xml(StringIO(f.read()))
   .....:

In [381]: df
Out[381]:
   category             title               author  year  price
0   cooking  Everyday Italian  Giada De Laurentiis  2005  30.00
1  children      Harry Potter         J K. Rowling  2005  29.99
2       web      Learning XML          Erik T. Ray  2003  39.95

In [382]: with open(file_path, "r") as f:
   .....:     sio = StringIO(f.read())
   .....:

In [383]: df = pd.read_xml(sio)

In [384]: df
Out[384]:
   category             title               author  year  price
0   cooking  Everyday Italian  Giada De Laurentiis  2005  30.00
1  children      Harry Potter         J K. Rowling  2005  29.99
2       web      Learning XML          Erik T. Ray  2003  39.95

In [385]: with open(file_path, "rb") as f:
   .....:     bio = BytesIO(f.read())
   .....:

In [386]: df = pd.read_xml(bio)

In [387]: df
Out[387]:
   category             title               author  year  price
0   cooking  Everyday Italian  Giada De Laurentiis  2005  30.00
1  children      Harry Potter         J K. Rowling  2005  29.99
2       web      Learning XML          Erik T. Ray  2003  39.95

In [388]: df = pd.read_xml(
   .....:     "s3://pmc-oa-opendata/oa_comm/xml/all/PMC1236943.xml",
   .....:     xpath=".//journal-meta",
   .....: )
   .....:

In [389]: df
Out[389]:
              journal-id              journal-title       issn  publisher
0  Cardiovasc Ultrasound  Cardiovascular Ultrasound  1476-7120        NaN

In [390]: df = pd.read_xml(file_path, xpath="//book[year=2005]")

In [391]: df
Out[391]:
   category             title               author  year  price
0   cooking  Everyday Italian  Giada De Laurentiis  2005  30.00
1  children      Harry Potter         J K. Rowling  2005  29.99

In [392]: df = pd.read_xml(file_path, elems_only=True)

In [393]: df
Out[393]:
              title               author  year  price
0  Everyday Italian  Giada De Laurentiis  2005  30.00
1      Harry Potter         J K. Rowling  2005  29.99
2      Learning XML          Erik T. Ray  2003  39.95

In [394]: df = pd.read_xml(file_path, attrs_only=True)

In [395]: df
Out[395]:
   category
0   cooking
1  children
2       web

In [396]: xml = """<?xml version='1.0' encoding='utf-8'?>
   .....: <doc:data xmlns:doc="https://example.com">
   .....:   <doc:row>
   .....:     <doc:shape>square</doc:shape>
   .....:     <doc:degrees>360</doc:degrees>
   .....:     <doc:sides>4.0</doc:sides>
   .....:   </doc:row>
   .....:   <doc:row>
   .....:     <doc:shape>circle</doc:shape>
   .....:     <doc:degrees>360</doc:degrees>
   .....:     <doc:sides/>
   .....:   </doc:row>
   .....:   <doc:row>
   .....:     <doc:shape>triangle</doc:shape>
   .....:     <doc:degrees>180</doc:degrees>
   .....:     <doc:sides>3.0</doc:sides>
   .....:   </doc:row>
   .....: </doc:data>"""
   .....:

In [397]: df = pd.read_xml(StringIO(xml),
   .....:                  xpath="//doc:row",
   .....:                  namespaces={"doc": "https://example.com"})
   .....:

In [398]: df
Out[398]:
      shape  degrees  sides
0    square      360    4.0
1    circle      360    NaN
2  triangle      180    3.0

In [399]: xml = """<?xml version='1.0' encoding='utf-8'?>
   .....: <data xmlns="https://example.com">
   .....:  <row>
   .....:    <shape>square</shape>
   .....:    <degrees>360</degrees>
   .....:    <sides>4.0</sides>
   .....:  </row>
   .....:  <row>
   .....:    <shape>circle</shape>
   .....:    <degrees>360</degrees>
   .....:    <sides/>
   .....:  </row>
   .....:  <row>
   .....:    <shape>triangle</shape>
   .....:    <degrees>180</degrees>
   .....:    <sides>3.0</sides>
   .....:  </row>
   .....: </data>"""
   .....:

In [400]: df = pd.read_xml(StringIO(xml),
   .....:                  xpath="//pandas:row",
   .....:                  namespaces={"pandas": "https://example.com"})
   .....:

In [401]: df
Out[401]:
      shape  degrees  sides
0    square      360    4.0
1    circle      360    NaN
2  triangle      180    3.0

In [402]: xml = """
   .....: <data>
   .....:   <row>
   .....:     <shape sides="4">square</shape>
   .....:     <degrees>360</degrees>
   .....:   </row>
   .....:   <row>
   .....:     <shape sides="0">circle</shape>
   .....:     <degrees>360</degrees>
   .....:   </row>
   .....:   <row>
   .....:     <shape sides="3">triangle</shape>
   .....:     <degrees>180</degrees>
   .....:   </row>
   .....: </data>"""
   .....:

In [403]: df = pd.read_xml(StringIO(xml), xpath="./row")

In [404]: df
Out[404]:
      shape  degrees
0    square      360
1    circle      360
2  triangle      180

In [405]: xml = """<?xml version='1.0' encoding='utf-8'?>
   .....:  <response>
   .....:   <row>
   .....:     <station id="40850" name="Library"/>
   .....:     <month>2020-09-01T00:00:00</month>
   .....:     <rides>
   .....:       <avg_weekday_rides>864.2</avg_weekday_rides>
   .....:       <avg_saturday_rides>534</avg_saturday_rides>
   .....:       <avg_sunday_holiday_rides>417.2</avg_sunday_holiday_rides>
   .....:     </rides>
   .....:   </row>
   .....:   <row>
   .....:     <station id="41700" name="Washington/Wabash"/>
   .....:     <month>2020-09-01T00:00:00</month>
   .....:     <rides>
   .....:       <avg_weekday_rides>2707.4</avg_weekday_rides>
   .....:       <avg_saturday_rides>1909.8</avg_saturday_rides>
   .....:       <avg_sunday_holiday_rides>1438.6</avg_sunday_holiday_rides>
   .....:     </rides>
   .....:   </row>
   .....:   <row>
   .....:     <station id="40380" name="Clark/Lake"/>
   .....:     <month>2020-09-01T00:00:00</month>
   .....:     <rides>
   .....:       <avg_weekday_rides>2949.6</avg_weekday_rides>
   .....:       <avg_saturday_rides>1657</avg_saturday_rides>
   .....:       <avg_sunday_holiday_rides>1453.8</avg_sunday_holiday_rides>
   .....:     </rides>
   .....:   </row>
   .....:  </response>"""
   .....:

In [406]: xsl = """<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
   .....:    <xsl:output method="xml" omit-xml-declaration="no" indent="yes"/>
   .....:    <xsl:strip-space elements="*"/>
   .....:    <xsl:template match="/response">
   .....:       <xsl:copy>
   .....:         <xsl:apply-templates select="row"/>
   .....:       </xsl:copy>
   .....:    </xsl:template>
   .....:    <xsl:template match="row">
   .....:       <xsl:copy>
   .....:         <station_id><xsl:value-of select="station/@id"/></station_id>
   .....:         <station_name><xsl:value-of select="station/@name"/></station_name>
   .....:         <xsl:copy-of select="month|rides/*"/>
   .....:       </xsl:copy>
   .....:    </xsl:template>
   .....:  </xsl:stylesheet>"""
   .....:

In [407]: output = """<?xml version='1.0' encoding='utf-8'?>
   .....:  <response>
   .....:    <row>
   .....:       <station_id>40850</station_id>
   .....:       <station_name>Library</station_name>
   .....:       <month>2020-09-01T00:00:00</month>
   .....:       <avg_weekday_rides>864.2</avg_weekday_rides>
   .....:       <avg_saturday_rides>534</avg_saturday_rides>
   .....:       <avg_sunday_holiday_rides>417.2</avg_sunday_holiday_rides>
   .....:    </row>
   .....:    <row>
   .....:       <station_id>41700</station_id>
   .....:       <station_name>Washington/Wabash</station_name>
   .....:       <month>2020-09-01T00:00:00</month>
   .....:       <avg_weekday_rides>2707.4</avg_weekday_rides>
   .....:       <avg_saturday_rides>1909.8</avg_saturday_rides>
   .....:       <avg_sunday_holiday_rides>1438.6</avg_sunday_holiday_rides>
   .....:    </row>
   .....:    <row>
   .....:       <station_id>40380</station_id>
   .....:       <station_name>Clark/Lake</station_name>
   .....:       <month>2020-09-01T00:00:00</month>
   .....:       <avg_weekday_rides>2949.6</avg_weekday_rides>
   .....:       <avg_saturday_rides>1657</avg_saturday_rides>
   .....:       <avg_sunday_holiday_rides>1453.8</avg_sunday_holiday_rides>
   .....:    </row>
   .....:  </response>"""
   .....:

In [408]: df = pd.read_xml(StringIO(xml), stylesheet=xsl)

In [409]: df
Out[409]:
   station_id       station_name  ... avg_saturday_rides  avg_sunday_holiday_rides
0       40850            Library  ...              534.0                     417.2
1       41700  Washington/Wabash  ...             1909.8                    1438.6
2       40380         Clark/Lake  ...             1657.0                    1453.8

[3 rows x 6 columns]

In [1]: df = pd.read_xml(
...         "/path/to/downloaded/enwikisource-latest-pages-articles.xml",
...         iterparse = {"page": ["title", "ns", "id"]}
...     )
...     df
Out[2]:
                                                     title   ns        id
0                                       Gettysburg Address    0     21450
1                                                Main Page    0     42950
2                            Declaration by United Nations    0      8435
3             Constitution of the United States of America    0      8435
4                     Declaration of Independence (Israel)    0     17858
...                                                    ...  ...       ...
3578760               Page:Black cat 1897 07 v2 n10.pdf/17  104    219649
3578761               Page:Black cat 1897 07 v2 n10.pdf/43  104    219649
3578762               Page:Black cat 1897 07 v2 n10.pdf/44  104    219649
3578763      The History of Tom Jones, a Foundling/Book IX    0  12084291
3578764  Page:Shakespeare of Stratford (1926) Yale.djvu/91  104     21450

[3578765 rows x 3 columns]

In [410]: geom_df = pd.DataFrame(
   .....:     {
   .....:         "shape": ["square", "circle", "triangle"],
   .....:         "degrees": [360, 360, 180],
   .....:         "sides": [4, np.nan, 3],
   .....:     }
   .....: )
   .....:

In [411]: print(geom_df.to_xml())
<?xml version='1.0' encoding='utf-8'?>
<data>
  <row>
    <index>0</index>
    <shape>square</shape>
    <degrees>360</degrees>
    <sides>4.0</sides>
  </row>
  <row>
    <index>1</index>
    <shape>circle</shape>
    <degrees>360</degrees>
    <sides/>
  </row>
  <row>
    <index>2</index>
    <shape>triangle</shape>
    <degrees>180</degrees>
    <sides>3.0</sides>
  </row>
</data>

In [412]: print(geom_df.to_xml(root_name="geometry", row_name="objects"))
<?xml version='1.0' encoding='utf-8'?>
<geometry>
  <objects>
    <index>0</index>
    <shape>square</shape>
    <degrees>360</degrees>
    <sides>4.0</sides>
  </objects>
  <objects>
    <index>1</index>
    <shape>circle</shape>
    <degrees>360</degrees>
    <sides/>
  </objects>
  <objects>
    <index>2</index>
    <shape>triangle</shape>
    <degrees>180</degrees>
    <sides>3.0</sides>
  </objects>
</geometry>

In [413]: print(geom_df.to_xml(attr_cols=geom_df.columns.tolist()))
<?xml version='1.0' encoding='utf-8'?>
<data>
  <row index="0" shape="square" degrees="360" sides="4.0"/>
  <row index="1" shape="circle" degrees="360"/>
  <row index="2" shape="triangle" degrees="180" sides="3.0"/>
</data>

In [414]: print(
   .....:     geom_df.to_xml(
   .....:         index=False,
   .....:         attr_cols=['shape'],
   .....:         elem_cols=['degrees', 'sides'])
   .....: )
   .....:
<?xml version='1.0' encoding='utf-8'?>
<data>
  <row shape="square">
    <degrees>360</degrees>
    <sides>4.0</sides>
  </row>
  <row shape="circle">
    <degrees>360</degrees>
    <sides/>
  </row>
  <row shape="triangle">
    <degrees>180</degrees>
    <sides>3.0</sides>
  </row>
</data>

In [415]: ext_geom_df = pd.DataFrame(
   .....:     {
   .....:         "type": ["polygon", "other", "polygon"],
   .....:         "shape": ["square", "circle", "triangle"],
   .....:         "degrees": [360, 360, 180],
   .....:         "sides": [4, np.nan, 3],
   .....:     }
   .....: )
   .....:

In [416]: pvt_df = ext_geom_df.pivot_table(index='shape',
   .....:                                  columns='type',
   .....:                                  values=['degrees', 'sides'],
   .....:                                  aggfunc='sum')
   .....:

In [417]: pvt_df
Out[417]:
         degrees         sides
type       other polygon other polygon
shape
circle     360.0     NaN   0.0     NaN
square       NaN   360.0   NaN     4.0
triangle     NaN   180.0   NaN     3.0

In [418]: print(pvt_df.to_xml())
<?xml version='1.0' encoding='utf-8'?>
<data>
  <row>
    <shape>circle</shape>
    <degrees_other>360.0</degrees_other>
    <degrees_polygon/>
    <sides_other>0.0</sides_other>
    <sides_polygon/>
  </row>
  <row>
    <shape>square</shape>
    <degrees_other/>
    <degrees_polygon>360.0</degrees_polygon>
    <sides_other/>
    <sides_polygon>4.0</sides_polygon>
  </row>
  <row>
    <shape>triangle</shape>
    <degrees_other/>
    <degrees_polygon>180.0</degrees_polygon>
    <sides_other/>
    <sides_polygon>3.0</sides_polygon>
  </row>
</data>

In [419]: print(geom_df.to_xml(namespaces={"": "https://example.com"}))
<?xml version='1.0' encoding='utf-8'?>
<data xmlns="https://example.com">
  <row>
    <index>0</index>
    <shape>square</shape>
    <degrees>360</degrees>
    <sides>4.0</sides>
  </row>
  <row>
    <index>1</index>
    <shape>circle</shape>
    <degrees>360</degrees>
    <sides/>
  </row>
  <row>
    <index>2</index>
    <shape>triangle</shape>
    <degrees>180</degrees>
    <sides>3.0</sides>
  </row>
</data>

In [420]: print(
   .....:     geom_df.to_xml(namespaces={"doc": "https://example.com"},
   .....:                    prefix="doc")
   .....: )
   .....:
<?xml version='1.0' encoding='utf-8'?>
<doc:data xmlns:doc="https://example.com">
  <doc:row>
    <doc:index>0</doc:index>
    <doc:shape>square</doc:shape>
    <doc:degrees>360</doc:degrees>
    <doc:sides>4.0</doc:sides>
  </doc:row>
  <doc:row>
    <doc:index>1</doc:index>
    <doc:shape>circle</doc:shape>
    <doc:degrees>360</doc:degrees>
    <doc:sides/>
  </doc:row>
  <doc:row>
    <doc:index>2</doc:index>
    <doc:shape>triangle</doc:shape>
    <doc:degrees>180</doc:degrees>
    <doc:sides>3.0</doc:sides>
  </doc:row>
</doc:data>

In [421]: print(
   .....:     geom_df.to_xml(xml_declaration=False,
   .....:                    pretty_print=False)
   .....: )
   .....:
<data><row><index>0</index><shape>square</shape><degrees>360</degrees><sides>4.0</sides></row><row><index>1</index><shape>circle</shape><degrees>360</degrees><sides/></row><row><index>2</index><shape>triangle</shape><degrees>180</degrees><sides>3.0</sides></row></data>

In [422]: xsl = """<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
   .....:    <xsl:output method="xml" omit-xml-declaration="no" indent="yes"/>
   .....:    <xsl:strip-space elements="*"/>
   .....:    <xsl:template match="/data">
   .....:      <geometry>
   .....:        <xsl:apply-templates select="row"/>
   .....:      </geometry>
   .....:    </xsl:template>
   .....:    <xsl:template match="row">
   .....:      <object index="{index}">
   .....:        <xsl:if test="shape!='circle'">
   .....:            <xsl:attribute name="type">polygon</xsl:attribute>
   .....:        </xsl:if>
   .....:        <xsl:copy-of select="shape"/>
   .....:        <property>
   .....:            <xsl:copy-of select="degrees|sides"/>
   .....:        </property>
   .....:      </object>
   .....:    </xsl:template>
   .....:  </xsl:stylesheet>"""
   .....:

In [423]: print(geom_df.to_xml(stylesheet=xsl))
<?xml version="1.0"?>
<geometry>
  <object index="0" type="polygon">
    <shape>square</shape>
    <property>
      <degrees>360</degrees>
      <sides>4.0</sides>
    </property>
  </object>
  <object index="1">
    <shape>circle</shape>
    <property>
      <degrees>360</degrees>
      <sides/>
    </property>
  </object>
  <object index="2" type="polygon">
    <shape>triangle</shape>
    <property>
      <degrees>180</degrees>
      <sides>3.0</sides>
    </property>
  </object>
</geometry>

# Returns a DataFrame
pd.read_excel("path_to_file.xls", sheet_name="Sheet1")

xlsx = pd.ExcelFile("path_to_file.xls")
df = pd.read_excel(xlsx, "Sheet1")

with pd.ExcelFile("path_to_file.xls") as xls:
    df1 = pd.read_excel(xls, "Sheet1")
    df2 = pd.read_excel(xls, "Sheet2")

data = {}
# For when Sheet1's format differs from Sheet2
with pd.ExcelFile("path_to_file.xls") as xls:
    data["Sheet1"] = pd.read_excel(xls, "Sheet1", index_col=None, na_values=["NA"])
    data["Sheet2"] = pd.read_excel(xls, "Sheet2", index_col=1)

# using the ExcelFile class
data = {}
with pd.ExcelFile("path_to_file.xls") as xls:
    data["Sheet1"] = pd.read_excel(xls, "Sheet1", index_col=None, na_values=["NA"])
    data["Sheet2"] = pd.read_excel(xls, "Sheet2", index_col=None, na_values=["NA"])

# equivalent using the read_excel function
data = pd.read_excel(
    "path_to_file.xls", ["Sheet1", "Sheet2"], index_col=None, na_values=["NA"]
)

import xlrd

xlrd_book = xlrd.open_workbook("path_to_file.xls", on_demand=True)
with pd.ExcelFile(xlrd_book) as xls:
    df1 = pd.read_excel(xls, "Sheet1")
    df2 = pd.read_excel(xls, "Sheet2")

# Returns a DataFrame
pd.read_excel("path_to_file.xls", "Sheet1", index_col=None, na_values=["NA"])

# Returns a DataFrame
pd.read_excel("path_to_file.xls", 0, index_col=None, na_values=["NA"])

# Returns a DataFrame
pd.read_excel("path_to_file.xls")

# Returns a dictionary of DataFrames
pd.read_excel("path_to_file.xls", sheet_name=None)

# Returns the 1st and 4th sheet, as a dictionary of DataFrames.
pd.read_excel("path_to_file.xls", sheet_name=["Sheet1", 3])

In [424]: df = pd.DataFrame(
   .....:     {"a": [1, 2, 3, 4], "b": [5, 6, 7, 8]},
   .....:     index=pd.MultiIndex.from_product([["a", "b"], ["c", "d"]]),
   .....: )
   .....:

In [425]: df.to_excel("path_to_file.xlsx")

In [426]: df = pd.read_excel("path_to_file.xlsx", index_col=[0, 1])

In [427]: df
Out[427]:
     a  b
a c  1  5
  d  2  6
b c  3  7
  d  4  8

In [428]: df.index = df.index.set_names(["lvl1", "lvl2"])

In [429]: df.to_excel("path_to_file.xlsx")

In [430]: df = pd.read_excel("path_to_file.xlsx", index_col=[0, 1])

In [431]: df
Out[431]:
           a  b
lvl1 lvl2
a    c     1  5
     d     2  6
b    c     3  7
     d     4  8

In [432]: df.columns = pd.MultiIndex.from_product([["a"], ["b", "d"]], names=["c1", "c2"])

In [433]: df.to_excel("path_to_file.xlsx")

In [434]: df = pd.read_excel("path_to_file.xlsx", index_col=[0, 1], header=[0, 1])

In [435]: df
Out[435]:
c1         a
c2         b  d
lvl1 lvl2
a    c     1  5
     d     2  6
b    c     3  7
     d     4  8

pd.read_excel("path_to_file.xls", "Sheet1", usecols="A,C:E")

pd.read_excel("path_to_file.xls", "Sheet1", usecols=[0, 2, 3])

pd.read_excel("path_to_file.xls", "Sheet1", usecols=["foo", "bar"])

pd.read_excel("path_to_file.xls", "Sheet1", usecols=lambda x: x.isalpha())

pd.read_excel("path_to_file.xls", "Sheet1", parse_dates=["date_strings"])

pd.read_excel("path_to_file.xls", "Sheet1", converters={"MyBools": bool})

def cfun(x):
    return int(x) if x else -1


pd.read_excel("path_to_file.xls", "Sheet1", converters={"MyInts": cfun})

pd.read_excel("path_to_file.xls", dtype={"MyInts": "int64", "MyText": str})

df.to_excel("path_to_file.xlsx", sheet_name="Sheet1")

df.to_excel("path_to_file.xlsx", index_label="label", merge_cells=False)

with pd.ExcelWriter("path_to_file.xlsx") as writer:
    df1.to_excel(writer, sheet_name="Sheet1")
    df2.to_excel(writer, sheet_name="Sheet2")

from io import BytesIO

bio = BytesIO()

# By setting the 'engine' in the ExcelWriter constructor.
writer = pd.ExcelWriter(bio, engine="xlsxwriter")
df.to_excel(writer, sheet_name="Sheet1")

# Save the workbook
writer.save()

# Seek to the beginning and read to copy the workbook to a variable in memory
bio.seek(0)
workbook = bio.read()

# By setting the 'engine' in the DataFrame 'to_excel()' methods.
df.to_excel("path_to_file.xlsx", sheet_name="Sheet1", engine="xlsxwriter")

# By setting the 'engine' in the ExcelWriter constructor.
writer = pd.ExcelWriter("path_to_file.xlsx", engine="xlsxwriter")

# Or via pandas configuration.
from pandas import options  # noqa: E402

options.io.excel.xlsx.writer = "xlsxwriter"

df.to_excel("path_to_file.xlsx", sheet_name="Sheet1")

In [439]: df = pd.DataFrame(
   .....:     {
   .....:         "A": np.random.randn(1000),
   .....:         "B": "foo",
   .....:         "C": pd.date_range("20130101", periods=1000, freq="s"),
   .....:     }
   .....: )
   .....:

In [440]: df
Out[440]:
            A    B                   C
0   -0.317441  foo 2013-01-01 00:00:00
1   -1.236269  foo 2013-01-01 00:00:01
2    0.896171  foo 2013-01-01 00:00:02
3   -0.487602  foo 2013-01-01 00:00:03
4   -0.082240  foo 2013-01-01 00:00:04
..        ...  ...                 ...
995 -0.171092  foo 2013-01-01 00:16:35
996  1.786173  foo 2013-01-01 00:16:36
997 -0.575189  foo 2013-01-01 00:16:37
998  0.820750  foo 2013-01-01 00:16:38
999 -1.256530  foo 2013-01-01 00:16:39

[1000 rows x 3 columns]

In [441]: df.to_pickle("data.pkl.compress", compression="gzip")

In [442]: rt = pd.read_pickle("data.pkl.compress", compression="gzip")

In [443]: rt
Out[443]:
            A    B                   C
0   -0.317441  foo 2013-01-01 00:00:00
1   -1.236269  foo 2013-01-01 00:00:01
2    0.896171  foo 2013-01-01 00:00:02
3   -0.487602  foo 2013-01-01 00:00:03
4   -0.082240  foo 2013-01-01 00:00:04
..        ...  ...                 ...
995 -0.171092  foo 2013-01-01 00:16:35
996  1.786173  foo 2013-01-01 00:16:36
997 -0.575189  foo 2013-01-01 00:16:37
998  0.820750  foo 2013-01-01 00:16:38
999 -1.256530  foo 2013-01-01 00:16:39

[1000 rows x 3 columns]

In [444]: df.to_pickle("data.pkl.xz", compression="infer")

In [445]: rt = pd.read_pickle("data.pkl.xz", compression="infer")

In [446]: rt
Out[446]:
            A    B                   C
0   -0.317441  foo 2013-01-01 00:00:00
1   -1.236269  foo 2013-01-01 00:00:01
2    0.896171  foo 2013-01-01 00:00:02
3   -0.487602  foo 2013-01-01 00:00:03
4   -0.082240  foo 2013-01-01 00:00:04
..        ...  ...                 ...
995 -0.171092  foo 2013-01-01 00:16:35
996  1.786173  foo 2013-01-01 00:16:36
997 -0.575189  foo 2013-01-01 00:16:37
998  0.820750  foo 2013-01-01 00:16:38
999 -1.256530  foo 2013-01-01 00:16:39

[1000 rows x 3 columns]

In [447]: df.to_pickle("data.pkl.gz")

In [448]: rt = pd.read_pickle("data.pkl.gz")

In [449]: rt
Out[449]:
            A    B                   C
0   -0.317441  foo 2013-01-01 00:00:00
1   -1.236269  foo 2013-01-01 00:00:01
2    0.896171  foo 2013-01-01 00:00:02
3   -0.487602  foo 2013-01-01 00:00:03
4   -0.082240  foo 2013-01-01 00:00:04
..        ...  ...                 ...
995 -0.171092  foo 2013-01-01 00:16:35
996  1.786173  foo 2013-01-01 00:16:36
997 -0.575189  foo 2013-01-01 00:16:37
998  0.820750  foo 2013-01-01 00:16:38
999 -1.256530  foo 2013-01-01 00:16:39

[1000 rows x 3 columns]

In [450]: df["A"].to_pickle("s1.pkl.bz2")

In [451]: rt = pd.read_pickle("s1.pkl.bz2")

In [452]: rt
Out[452]:
0     -0.317441
1     -1.236269
2      0.896171
3     -0.487602
4     -0.082240
         ...
995   -0.171092
996    1.786173
997   -0.575189
998    0.820750
999   -1.256530
Name: A, Length: 1000, dtype: float64

In [453]: df.to_pickle("data.pkl.gz", compression={"method": "gzip", "compresslevel": 1})

In [470]: df_tl = pd.DataFrame({"A": list(range(5)), "B": list(range(5))})

In [471]: df_tl.to_hdf("store_tl.h5", key="table", append=True)

In [472]: pd.read_hdf("store_tl.h5", "table", where=["index>2"])
Out[472]:
   A  B
3  3  3
4  4  4

In [473]: df_with_missing = pd.DataFrame(
   .....:     {
   .....:         "col1": [0, np.nan, 2],
   .....:         "col2": [1, np.nan, np.nan],
   .....:     }
   .....: )
   .....:

In [474]: df_with_missing
Out[474]:
   col1  col2
0   0.0   1.0
1   NaN   NaN
2   2.0   NaN

In [475]: df_with_missing.to_hdf("file.h5", key="df_with_missing", format="table", mode="w")

In [476]: pd.read_hdf("file.h5", "df_with_missing")
Out[476]:
   col1  col2
0   0.0   1.0
1   NaN   NaN
2   2.0   NaN

In [477]: df_with_missing.to_hdf(
   .....:     "file.h5", key="df_with_missing", format="table", mode="w", dropna=True
   .....: )
   .....:

In [478]: pd.read_hdf("file.h5", "df_with_missing")
Out[478]:
   col1  col2
0   0.0   1.0
2   2.0   NaN

In [479]: pd.DataFrame(np.random.randn(10, 2)).to_hdf("test_fixed.h5", key="df")

In [480]: pd.read_hdf("test_fixed.h5", "df", where="index>5")
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[480], line 1
----> 1 pd.read_hdf("test_fixed.h5", "df", where="index>5")

File ~/work/pandas/pandas/pandas/io/pytables.py:452, in read_hdf(path_or_buf, key, mode, errors, where, start, stop, columns, iterator, chunksize, **kwargs)
    447                 raise ValueError(
    448                     "key must be provided when HDF5 "
    449                     "file contains multiple datasets."
    450                 )
    451         key = candidate_only_group._v_pathname
--> 452     return store.select(
    453         key,
    454         where=where,
    455         start=start,
    456         stop=stop,
    457         columns=columns,
    458         iterator=iterator,
    459         chunksize=chunksize,
    460         auto_close=auto_close,
    461     )
    462 except (ValueError, TypeError, LookupError):
    463     if not isinstance(path_or_buf, HDFStore):
    464         # if there is an error, close the store if we opened it.

File ~/work/pandas/pandas/pandas/io/pytables.py:906, in HDFStore.select(self, key, where, start, stop, columns, iterator, chunksize, auto_close)
    892 # create the iterator
    893 it = TableIterator(
    894     self,
    895     s,
   (...)
    903     auto_close=auto_close,
    904 )
--> 906 return it.get_result()

File ~/work/pandas/pandas/pandas/io/pytables.py:2029, in TableIterator.get_result(self, coordinates)
   2026     where = self.where
   2028 # directly return the result
-> 2029 results = self.func(self.start, self.stop, where)
   2030 self.close()
   2031 return results

File ~/work/pandas/pandas/pandas/io/pytables.py:890, in HDFStore.select.<locals>.func(_start, _stop, _where)
    889 def func(_start, _stop, _where):
--> 890     return s.read(start=_start, stop=_stop, where=_where, columns=columns)

File ~/work/pandas/pandas/pandas/io/pytables.py:3278, in BlockManagerFixed.read(self, where, columns, start, stop)
   3270 def read(
   3271     self,
   3272     where=None,
   (...)
   3276 ) -> DataFrame:
   3277     # start, stop applied to rows, so 0th axis only
-> 3278     self.validate_read(columns, where)
   3279     select_axis = self.obj_type()._get_block_manager_axis(0)
   3281     axes = []

File ~/work/pandas/pandas/pandas/io/pytables.py:2922, in GenericFixed.validate_read(self, columns, where)
   2917     raise TypeError(
   2918         "cannot pass a column specification when reading "
   2919         "a Fixed format store. this store must be selected in its entirety"
   2920     )
   2921 if where is not None:
-> 2922     raise TypeError(
   2923         "cannot pass a where specification when reading "
   2924         "from a Fixed format store. this store must be selected in its entirety"
   2925     )

TypeError: cannot pass a where specification when reading from a Fixed format store. this store must be selected in its entirety

In [481]: store = pd.HDFStore("store.h5")

In [482]: df1 = df[0:4]

In [483]: df2 = df[4:]

# append data (creates a table automatically)
In [484]: store.append("df", df1)

In [485]: store.append("df", df2)

In [486]: store
Out[486]:
<class 'pandas.io.pytables.HDFStore'>
File path: store.h5

# select the entire object
In [487]: store.select("df")
Out[487]:
                   A         B         C
2000-01-01  0.858644 -0.851236  1.058006
2000-01-02 -0.080372 -1.268121  1.561967
2000-01-03  0.816983  1.965656 -1.169408
2000-01-04  0.712795 -0.062433  0.736755
2000-01-05 -0.298721 -1.988045  1.475308
2000-01-06  1.103675  1.382242 -0.650762
2000-01-07 -0.729161 -0.142928 -1.063038
2000-01-08 -1.005977  0.465222 -0.094517

# the type of stored data
In [488]: store.root.df._v_attrs.pandas_type
Out[488]: 'frame_table'

In [489]: store.put("foo/bar/bah", df)

In [490]: store.append("food/orange", df)

In [491]: store.append("food/apple", df)

In [492]: store
Out[492]:
<class 'pandas.io.pytables.HDFStore'>
File path: store.h5

# a list of keys are returned
In [493]: store.keys()
Out[493]: ['/df', '/food/apple', '/food/orange', '/foo/bar/bah']

# remove all nodes under this level
In [494]: store.remove("food")

In [495]: store
Out[495]:
<class 'pandas.io.pytables.HDFStore'>
File path: store.h5

In [496]: for (path, subgroups, subkeys) in store.walk():
   .....:     for subgroup in subgroups:
   .....:         print("GROUP: {}/{}".format(path, subgroup))
   .....:     for subkey in subkeys:
   .....:         key = "/".join([path, subkey])
   .....:         print("KEY: {}".format(key))
   .....:         print(store.get(key))
   .....:
GROUP: /foo
KEY: /df
                   A         B         C
2000-01-01  0.858644 -0.851236  1.058006
2000-01-02 -0.080372 -1.268121  1.561967
2000-01-03  0.816983  1.965656 -1.169408
2000-01-04  0.712795 -0.062433  0.736755
2000-01-05 -0.298721 -1.988045  1.475308
2000-01-06  1.103675  1.382242 -0.650762
2000-01-07 -0.729161 -0.142928 -1.063038
2000-01-08 -1.005977  0.465222 -0.094517
GROUP: /foo/bar
KEY: /foo/bar/bah
                   A         B         C
2000-01-01  0.858644 -0.851236  1.058006
2000-01-02 -0.080372 -1.268121  1.561967
2000-01-03  0.816983  1.965656 -1.169408
2000-01-04  0.712795 -0.062433  0.736755
2000-01-05 -0.298721 -1.988045  1.475308
2000-01-06  1.103675  1.382242 -0.650762
2000-01-07 -0.729161 -0.142928 -1.063038
2000-01-08 -1.005977  0.465222 -0.094517

In [497]: store.foo.bar.bah
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[497], line 1
----> 1 store.foo.bar.bah

File ~/work/pandas/pandas/pandas/io/pytables.py:613, in HDFStore.__getattr__(self, name)
    611 """allow attribute access to get stores"""
    612 try:
--> 613     return self.get(name)
    614 except (KeyError, ClosedFileError):
    615     pass

File ~/work/pandas/pandas/pandas/io/pytables.py:813, in HDFStore.get(self, key)
    811 if group is None:
    812     raise KeyError(f"No object named {key} in the file")
--> 813 return self._read_group(group)

File ~/work/pandas/pandas/pandas/io/pytables.py:1878, in HDFStore._read_group(self, group)
   1877 def _read_group(self, group: Node):
-> 1878     s = self._create_storer(group)
   1879     s.infer_axes()
   1880     return s.read()

File ~/work/pandas/pandas/pandas/io/pytables.py:1752, in HDFStore._create_storer(self, group, format, value, encoding, errors)
   1750         tt = "generic_table"
   1751     else:
-> 1752         raise TypeError(
   1753             "cannot create a storer if the object is not existing "
   1754             "nor a value are passed"
   1755         )
   1756 else:
   1757     if isinstance(value, Series):

TypeError: cannot create a storer if the object is not existing nor a value are passed

# you can directly access the actual PyTables node but using the root node
In [498]: store.root.foo.bar.bah
Out[498]:
/foo/bar/bah (Group) ''
  children := ['axis0' (Array), 'axis1' (Array), 'block0_items' (Array), 'block0_values' (Array)]

In [499]: store["foo/bar/bah"]
Out[499]:
                   A         B         C
2000-01-01  0.858644 -0.851236  1.058006
2000-01-02 -0.080372 -1.268121  1.561967
2000-01-03  0.816983  1.965656 -1.169408
2000-01-04  0.712795 -0.062433  0.736755
2000-01-05 -0.298721 -1.988045  1.475308
2000-01-06  1.103675  1.382242 -0.650762
2000-01-07 -0.729161 -0.142928 -1.063038
2000-01-08 -1.005977  0.465222 -0.094517

In [500]: df_mixed = pd.DataFrame(
   .....:     {
   .....:         "A": np.random.randn(8),
   .....:         "B": np.random.randn(8),
   .....:         "C": np.array(np.random.randn(8), dtype="float32"),
   .....:         "string": "string",
   .....:         "int": 1,
   .....:         "bool": True,
   .....:         "datetime64": pd.Timestamp("20010102"),
   .....:     },
   .....:     index=list(range(8)),
   .....: )
   .....:

In [501]: df_mixed.loc[df_mixed.index[3:5], ["A", "B", "string", "datetime64"]] = np.nan

In [502]: store.append("df_mixed", df_mixed, min_itemsize={"values": 50})

In [503]: df_mixed1 = store.select("df_mixed")

In [504]: df_mixed1
Out[504]:
          A         B         C  ... int  bool                    datetime64
0  0.013747 -1.166078 -1.292080  ...   1  True 1970-01-01 00:00:00.978393600
1 -0.712009  0.247572  1.526911  ...   1  True 1970-01-01 00:00:00.978393600
2 -0.645096  1.687406  0.288504  ...   1  True 1970-01-01 00:00:00.978393600
3       NaN       NaN  0.097771  ...   1  True                           NaT
4       NaN       NaN  1.536408  ...   1  True                           NaT
5 -0.023202  0.043702  0.926790  ...   1  True 1970-01-01 00:00:00.978393600
6  2.359782  0.088224 -0.676448  ...   1  True 1970-01-01 00:00:00.978393600
7 -0.143428 -0.813360 -0.179724  ...   1  True 1970-01-01 00:00:00.978393600

[8 rows x 7 columns]

In [505]: df_mixed1.dtypes.value_counts()
Out[505]:
float64           2
float32           1
object            1
int64             1
bool              1
datetime64[ns]    1
Name: count, dtype: int64

# we have provided a minimum string column size
In [506]: store.root.df_mixed.table
Out[506]:
/df_mixed/table (Table(8,)) ''
  description := {
  "index": Int64Col(shape=(), dflt=0, pos=0),
  "values_block_0": Float64Col(shape=(2,), dflt=0.0, pos=1),
  "values_block_1": Float32Col(shape=(1,), dflt=0.0, pos=2),
  "values_block_2": StringCol(itemsize=50, shape=(1,), dflt=b'', pos=3),
  "values_block_3": Int64Col(shape=(1,), dflt=0, pos=4),
  "values_block_4": BoolCol(shape=(1,), dflt=False, pos=5),
  "values_block_5": Int64Col(shape=(1,), dflt=0, pos=6)}
  byteorder := 'little'
  chunkshape := (689,)
  autoindex := True
  colindexes := {
    "index": Index(6, mediumshuffle, zlib(1)).is_csi=False}

In [507]: index = pd.MultiIndex(
   .....:    levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
   .....:    codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
   .....:    names=["foo", "bar"],
   .....: )
   .....:

In [508]: df_mi = pd.DataFrame(np.random.randn(10, 3), index=index, columns=["A", "B", "C"])

In [509]: df_mi
Out[509]:
                  A         B         C
foo bar
foo one   -1.303456 -0.642994 -0.649456
    two    1.012694  0.414147  1.950460
    three  1.094544 -0.802899 -0.583343
bar one    0.410395  0.618321  0.560398
    two    1.434027 -0.033270  0.343197
baz two   -1.646063 -0.695847 -0.429156
    three -0.244688 -1.428229 -0.138691
qux one    1.866184 -1.446617  0.036660
    two   -1.660522  0.929553 -1.298649
    three  3.565769  0.682402  1.041927

In [510]: store.append("df_mi", df_mi)

In [511]: store.select("df_mi")
Out[511]:
                  A         B         C
foo bar
foo one   -1.303456 -0.642994 -0.649456
    two    1.012694  0.414147  1.950460
    three  1.094544 -0.802899 -0.583343
bar one    0.410395  0.618321  0.560398
    two    1.434027 -0.033270  0.343197
baz two   -1.646063 -0.695847 -0.429156
    three -0.244688 -1.428229 -0.138691
qux one    1.866184 -1.446617  0.036660
    two   -1.660522  0.929553 -1.298649
    three  3.565769  0.682402  1.041927

# the levels are automatically included as data columns
In [512]: store.select("df_mi", "foo=bar")
Out[512]:
                A         B         C
foo bar
bar one  0.410395  0.618321  0.560398
    two  1.434027 -0.033270  0.343197

string = "HolyMoly'"
store.select("df", "index == string")

string = "HolyMoly'"
store.select('df', f'index == {string}')

store.select("df", "index == %r" % string)

In [513]: dfq = pd.DataFrame(
   .....:     np.random.randn(10, 4),
   .....:     columns=list("ABCD"),
   .....:     index=pd.date_range("20130101", periods=10),
   .....: )
   .....:

In [514]: store.append("dfq", dfq, format="table", data_columns=True)

In [515]: store.select("dfq", "index>pd.Timestamp('20130104') & columns=['A', 'B']")
Out[515]:
                   A         B
2013-01-05 -0.830545 -0.457071
2013-01-06  0.431186  1.049421
2013-01-07  0.617509 -0.811230
2013-01-08  0.947422 -0.671233
2013-01-09 -0.183798 -1.211230
2013-01-10  0.361428  0.887304

In [516]: store.select("dfq", where="A>0 or C>0")
Out[516]:
                   A         B         C         D
2013-01-02  0.658179  0.362814 -0.917897  0.010165
2013-01-03  0.905122  1.848731 -1.184241  0.932053
2013-01-05 -0.830545 -0.457071  1.565581  1.148032
2013-01-06  0.431186  1.049421  0.383309  0.595013
2013-01-07  0.617509 -0.811230 -2.088563 -1.393500
2013-01-08  0.947422 -0.671233 -0.847097 -1.187785
2013-01-10  0.361428  0.887304  0.266457 -0.399641

In [517]: store.select("df", "columns=['A', 'B']")
Out[517]:
                   A         B
2000-01-01  0.858644 -0.851236
2000-01-02 -0.080372 -1.268121
2000-01-03  0.816983  1.965656
2000-01-04  0.712795 -0.062433
2000-01-05 -0.298721 -1.988045
2000-01-06  1.103675  1.382242
2000-01-07 -0.729161 -0.142928
2000-01-08 -1.005977  0.465222

In [518]: from datetime import timedelta

In [519]: dftd = pd.DataFrame(
   .....:     {
   .....:         "A": pd.Timestamp("20130101"),
   .....:         "B": [
   .....:             pd.Timestamp("20130101") + timedelta(days=i, seconds=10)
   .....:             for i in range(10)
   .....:         ],
   .....:     }
   .....: )
   .....:

In [520]: dftd["C"] = dftd["A"] - dftd["B"]

In [521]: dftd
Out[521]:
           A                   B                  C
0 2013-01-01 2013-01-01 00:00:10  -1 days +23:59:50
1 2013-01-01 2013-01-02 00:00:10  -2 days +23:59:50
2 2013-01-01 2013-01-03 00:00:10  -3 days +23:59:50
3 2013-01-01 2013-01-04 00:00:10  -4 days +23:59:50
4 2013-01-01 2013-01-05 00:00:10  -5 days +23:59:50
5 2013-01-01 2013-01-06 00:00:10  -6 days +23:59:50
6 2013-01-01 2013-01-07 00:00:10  -7 days +23:59:50
7 2013-01-01 2013-01-08 00:00:10  -8 days +23:59:50
8 2013-01-01 2013-01-09 00:00:10  -9 days +23:59:50
9 2013-01-01 2013-01-10 00:00:10 -10 days +23:59:50

In [522]: store.append("dftd", dftd, data_columns=True)

In [523]: store.select("dftd", "C<'-3.5D'")
Out[523]:
                              A                   B                  C
4 1970-01-01 00:00:01.356998400 2013-01-05 00:00:10  -5 days +23:59:50
5 1970-01-01 00:00:01.356998400 2013-01-06 00:00:10  -6 days +23:59:50
6 1970-01-01 00:00:01.356998400 2013-01-07 00:00:10  -7 days +23:59:50
7 1970-01-01 00:00:01.356998400 2013-01-08 00:00:10  -8 days +23:59:50
8 1970-01-01 00:00:01.356998400 2013-01-09 00:00:10  -9 days +23:59:50
9 1970-01-01 00:00:01.356998400 2013-01-10 00:00:10 -10 days +23:59:50

In [524]: df_mi.index.names
Out[524]: FrozenList(['foo', 'bar'])

In [525]: store.select("df_mi", "foo=baz and bar=two")
Out[525]:
                A         B         C
foo bar
baz two -1.646063 -0.695847 -0.429156

In [526]: index = pd.MultiIndex(
   .....:     levels=[["foo", "bar", "baz", "qux"], ["one", "two", "three"]],
   .....:     codes=[[0, 0, 0, 1, 1, 2, 2, 3, 3, 3], [0, 1, 2, 0, 1, 1, 2, 0, 1, 2]],
   .....: )
   .....:

In [527]: df_mi_2 = pd.DataFrame(np.random.randn(10, 3), index=index, columns=["A", "B", "C"])

In [528]: df_mi_2
Out[528]:
                  A         B         C
foo one   -0.219582  1.186860 -1.437189
    two    0.053768  1.872644 -1.469813
    three -0.564201  0.876341  0.407749
bar one   -0.232583  0.179812  0.922152
    two   -1.820952 -0.641360  2.133239
baz two   -0.941248 -0.136307 -1.271305
    three -0.099774 -0.061438 -0.845172
qux one    0.465793  0.756995 -0.541690
    two   -0.802241  0.877657 -2.553831
    three  0.094899 -2.319519  0.293601

In [529]: store.append("df_mi_2", df_mi_2)

# the levels are automatically included as data columns with keyword level_n
In [530]: store.select("df_mi_2", "level_0=foo and level_1=two")
Out[530]:
                A         B         C
foo two  0.053768  1.872644 -1.469813

# we have automagically already created an index (in the first section)
In [531]: i = store.root.df.table.cols.index.index

In [532]: i.optlevel, i.kind
Out[532]: (6, 'medium')

# change an index by passing new parameters
In [533]: store.create_table_index("df", optlevel=9, kind="full")

In [534]: i = store.root.df.table.cols.index.index

In [535]: i.optlevel, i.kind
Out[535]: (9, 'full')

In [536]: df_1 = pd.DataFrame(np.random.randn(10, 2), columns=list("AB"))

In [537]: df_2 = pd.DataFrame(np.random.randn(10, 2), columns=list("AB"))

In [538]: st = pd.HDFStore("appends.h5", mode="w")

In [539]: st.append("df", df_1, data_columns=["B"], index=False)

In [540]: st.append("df", df_2, data_columns=["B"], index=False)

In [541]: st.get_storer("df").table
Out[541]:
/df/table (Table(20,)) ''
  description := {
  "index": Int64Col(shape=(), dflt=0, pos=0),
  "values_block_0": Float64Col(shape=(1,), dflt=0.0, pos=1),
  "B": Float64Col(shape=(), dflt=0.0, pos=2)}
  byteorder := 'little'
  chunkshape := (2730,)

In [542]: st.create_table_index("df", columns=["B"], optlevel=9, kind="full")

In [543]: st.get_storer("df").table
Out[543]:
/df/table (Table(20,)) ''
  description := {
  "index": Int64Col(shape=(), dflt=0, pos=0),
  "values_block_0": Float64Col(shape=(1,), dflt=0.0, pos=1),
  "B": Float64Col(shape=(), dflt=0.0, pos=2)}
  byteorder := 'little'
  chunkshape := (2730,)
  autoindex := True
  colindexes := {
    "B": Index(9, fullshuffle, zlib(1)).is_csi=True}

In [544]: st.close()

In [545]: df_dc = df.copy()

In [546]: df_dc["string"] = "foo"

In [547]: df_dc.loc[df_dc.index[4:6], "string"] = np.nan

In [548]: df_dc.loc[df_dc.index[7:9], "string"] = "bar"

In [549]: df_dc["string2"] = "cool"

In [550]: df_dc.loc[df_dc.index[1:3], ["B", "C"]] = 1.0

In [551]: df_dc
Out[551]:
                   A         B         C string string2
2000-01-01  0.858644 -0.851236  1.058006    foo    cool
2000-01-02 -0.080372  1.000000  1.000000    foo    cool
2000-01-03  0.816983  1.000000  1.000000    foo    cool
2000-01-04  0.712795 -0.062433  0.736755    foo    cool
2000-01-05 -0.298721 -1.988045  1.475308    NaN    cool
2000-01-06  1.103675  1.382242 -0.650762    NaN    cool
2000-01-07 -0.729161 -0.142928 -1.063038    foo    cool
2000-01-08 -1.005977  0.465222 -0.094517    bar    cool

# on-disk operations
In [552]: store.append("df_dc", df_dc, data_columns=["B", "C", "string", "string2"])

In [553]: store.select("df_dc", where="B > 0")
Out[553]:
                   A         B         C string string2
2000-01-02 -0.080372  1.000000  1.000000    foo    cool
2000-01-03  0.816983  1.000000  1.000000    foo    cool
2000-01-06  1.103675  1.382242 -0.650762    NaN    cool
2000-01-08 -1.005977  0.465222 -0.094517    bar    cool

# getting creative
In [554]: store.select("df_dc", "B > 0 & C > 0 & string == foo")
Out[554]:
                   A    B    C string string2
2000-01-02 -0.080372  1.0  1.0    foo    cool
2000-01-03  0.816983  1.0  1.0    foo    cool

# this is in-memory version of this type of selection
In [555]: df_dc[(df_dc.B > 0) & (df_dc.C > 0) & (df_dc.string == "foo")]
Out[555]:
                   A    B    C string string2
2000-01-02 -0.080372  1.0  1.0    foo    cool
2000-01-03  0.816983  1.0  1.0    foo    cool

# we have automagically created this index and the B/C/string/string2
# columns are stored separately as ``PyTables`` columns
In [556]: store.root.df_dc.table
Out[556]:
/df_dc/table (Table(8,)) ''
  description := {
  "index": Int64Col(shape=(), dflt=0, pos=0),
  "values_block_0": Float64Col(shape=(1,), dflt=0.0, pos=1),
  "B": Float64Col(shape=(), dflt=0.0, pos=2),
  "C": Float64Col(shape=(), dflt=0.0, pos=3),
  "string": StringCol(itemsize=3, shape=(), dflt=b'', pos=4),
  "string2": StringCol(itemsize=4, shape=(), dflt=b'', pos=5)}
  byteorder := 'little'
  chunkshape := (1680,)
  autoindex := True
  colindexes := {
    "index": Index(6, mediumshuffle, zlib(1)).is_csi=False,
    "B": Index(6, mediumshuffle, zlib(1)).is_csi=False,
    "C": Index(6, mediumshuffle, zlib(1)).is_csi=False,
    "string": Index(6, mediumshuffle, zlib(1)).is_csi=False,
    "string2": Index(6, mediumshuffle, zlib(1)).is_csi=False}

In [557]: for df in store.select("df", chunksize=3):
   .....:     print(df)
   .....:
                   A         B         C
2000-01-01  0.858644 -0.851236  1.058006
2000-01-02 -0.080372 -1.268121  1.561967
2000-01-03  0.816983  1.965656 -1.169408
                   A         B         C
2000-01-04  0.712795 -0.062433  0.736755
2000-01-05 -0.298721 -1.988045  1.475308
2000-01-06  1.103675  1.382242 -0.650762
                   A         B         C
2000-01-07 -0.729161 -0.142928 -1.063038
2000-01-08 -1.005977  0.465222 -0.094517

for df in pd.read_hdf("store.h5", "df", chunksize=3):
    print(df)

In [558]: dfeq = pd.DataFrame({"number": np.arange(1, 11)})

In [559]: dfeq
Out[559]:
   number
0       1
1       2
2       3
3       4
4       5
5       6
6       7
7       8
8       9
9      10

In [560]: store.append("dfeq", dfeq, data_columns=["number"])

In [561]: def chunks(l, n):
   .....:     return [l[i: i + n] for i in range(0, len(l), n)]
   .....:

In [562]: evens = [2, 4, 6, 8, 10]

In [563]: coordinates = store.select_as_coordinates("dfeq", "number=evens")

In [564]: for c in chunks(coordinates, 2):
   .....:     print(store.select("dfeq", where=c))
   .....:
   number
1       2
3       4
   number
5       6
7       8
   number
9      10

In [565]: store.select_column("df_dc", "index")
Out[565]:
0   2000-01-01
1   2000-01-02
2   2000-01-03
3   2000-01-04
4   2000-01-05
5   2000-01-06
6   2000-01-07
7   2000-01-08
Name: index, dtype: datetime64[ns]

In [566]: store.select_column("df_dc", "string")
Out[566]:
0    foo
1    foo
2    foo
3    foo
4    NaN
5    NaN
6    foo
7    bar
Name: string, dtype: object

In [567]: df_coord = pd.DataFrame(
   .....:     np.random.randn(1000, 2), index=pd.date_range("20000101", periods=1000)
   .....: )
   .....:

In [568]: store.append("df_coord", df_coord)

In [569]: c = store.select_as_coordinates("df_coord", "index > 20020101")

In [570]: c
Out[570]:
Index([732, 733, 734, 735, 736, 737, 738, 739, 740, 741,
       ...
       990, 991, 992, 993, 994, 995, 996, 997, 998, 999],
      dtype='int64', length=268)

In [571]: store.select("df_coord", where=c)
Out[571]:
                   0         1
2002-01-02  0.007717  1.168386
2002-01-03  0.759328 -0.638934
2002-01-04 -1.154018 -0.324071
2002-01-05 -0.804551 -1.280593
2002-01-06 -0.047208  1.260503
...              ...       ...
2002-09-22 -1.139583  0.344316
2002-09-23 -0.760643 -1.306704
2002-09-24  0.059018  1.775482
2002-09-25  1.242255 -0.055457
2002-09-26  0.410317  2.194489

[268 rows x 2 columns]

In [572]: df_mask = pd.DataFrame(
   .....:     np.random.randn(1000, 2), index=pd.date_range("20000101", periods=1000)
   .....: )
   .....:

In [573]: store.append("df_mask", df_mask)

In [574]: c = store.select_column("df_mask", "index")

In [575]: where = c[pd.DatetimeIndex(c).month == 5].index

In [576]: store.select("df_mask", where=where)
Out[576]:
                   0         1
2000-05-01  1.479511  0.516433
2000-05-02 -0.334984 -1.493537
2000-05-03  0.900321  0.049695
2000-05-04  0.614266 -1.077151
2000-05-05  0.233881  0.493246
...              ...       ...
2002-05-27  0.294122  0.457407
2002-05-28 -1.102535  1.215650
2002-05-29 -0.432911  0.753606
2002-05-30 -1.105212  2.311877
2002-05-31  2.567296  2.610691

[93 rows x 2 columns]

In [577]: store.get_storer("df_dc").nrows
Out[577]: 8

In [578]: df_mt = pd.DataFrame(
   .....:     np.random.randn(8, 6),
   .....:     index=pd.date_range("1/1/2000", periods=8),
   .....:     columns=["A", "B", "C", "D", "E", "F"],
   .....: )
   .....:

In [579]: df_mt["foo"] = "bar"

In [580]: df_mt.loc[df_mt.index[1], ("A", "B")] = np.nan

# you can also create the tables individually
In [581]: store.append_to_multiple(
   .....:     {"df1_mt": ["A", "B"], "df2_mt": None}, df_mt, selector="df1_mt"
   .....: )
   .....:

In [582]: store
Out[582]:
<class 'pandas.io.pytables.HDFStore'>
File path: store.h5

# individual tables were created
In [583]: store.select("df1_mt")
Out[583]:
                   A         B
2000-01-01  0.162291 -0.430489
2000-01-02       NaN       NaN
2000-01-03  0.429207 -1.099274
2000-01-04  1.869081 -1.466039
2000-01-05  0.092130 -1.726280
2000-01-06  0.266901 -0.036854
2000-01-07 -0.517871 -0.990317
2000-01-08 -0.231342  0.557402

In [584]: store.select("df2_mt")
Out[584]:
                   C         D         E         F  foo
2000-01-01 -2.502042  0.668149  0.460708  1.834518  bar
2000-01-02  0.130441 -0.608465  0.439872  0.506364  bar
2000-01-03 -1.069546  1.236277  0.116634 -1.772519  bar
2000-01-04  0.137462  0.313939  0.748471 -0.943009  bar
2000-01-05  0.836517  2.049798  0.562167  0.189952  bar
2000-01-06  1.112750 -0.151596  1.503311  0.939470  bar
2000-01-07 -0.294348  0.335844 -0.794159  1.495614  bar
2000-01-08  0.860312 -0.538674 -0.541986 -1.759606  bar

# as a multiple
In [585]: store.select_as_multiple(
   .....:     ["df1_mt", "df2_mt"],
   .....:     where=["A>0", "B>0"],
   .....:     selector="df1_mt",
   .....: )
   .....:
Out[585]:
Empty DataFrame
Columns: [A, B, C, D, E, F, foo]
Index: []

store_compressed = pd.HDFStore(
    "store_compressed.h5", complevel=9, complib="blosc:blosclz"
)

store.append("df", df, complib="zlib", complevel=5)

ptrepack --chunkshape=auto --propindexes --complevel=9 --complib=blosc in.h5 out.h5

In [586]: dfcat = pd.DataFrame(
   .....:     {"A": pd.Series(list("aabbcdba")).astype("category"), "B": np.random.randn(8)}
   .....: )
   .....:

In [587]: dfcat
Out[587]:
   A         B
0  a -1.520478
1  a -1.069391
2  b -0.551981
3  b  0.452407
4  c  0.409257
5  d  0.301911
6  b -0.640843
7  a -2.253022

In [588]: dfcat.dtypes
Out[588]:
A    category
B     float64
dtype: object

In [589]: cstore = pd.HDFStore("cats.h5", mode="w")

In [590]: cstore.append("dfcat", dfcat, format="table", data_columns=["A"])

In [591]: result = cstore.select("dfcat", where="A in ['b', 'c']")

In [592]: result
Out[592]:
   A         B
2  b -0.551981
3  b  0.452407
4  c  0.409257
6  b -0.640843

In [593]: result.dtypes
Out[593]:
A    category
B     float64
dtype: object

In [594]: dfs = pd.DataFrame({"A": "foo", "B": "bar"}, index=list(range(5)))

In [595]: dfs
Out[595]:
     A    B
0  foo  bar
1  foo  bar
2  foo  bar
3  foo  bar
4  foo  bar

# A and B have a size of 30
In [596]: store.append("dfs", dfs, min_itemsize=30)

In [597]: store.get_storer("dfs").table
Out[597]:
/dfs/table (Table(5,)) ''
  description := {
  "index": Int64Col(shape=(), dflt=0, pos=0),
  "values_block_0": StringCol(itemsize=30, shape=(2,), dflt=b'', pos=1)}
  byteorder := 'little'
  chunkshape := (963,)
  autoindex := True
  colindexes := {
    "index": Index(6, mediumshuffle, zlib(1)).is_csi=False}

# A is created as a data_column with a size of 30
# B is size is calculated
In [598]: store.append("dfs2", dfs, min_itemsize={"A": 30})

In [599]: store.get_storer("dfs2").table
Out[599]:
/dfs2/table (Table(5,)) ''
  description := {
  "index": Int64Col(shape=(), dflt=0, pos=0),
  "values_block_0": StringCol(itemsize=3, shape=(1,), dflt=b'', pos=1),
  "A": StringCol(itemsize=30, shape=(), dflt=b'', pos=2)}
  byteorder := 'little'
  chunkshape := (1598,)
  autoindex := True
  colindexes := {
    "index": Index(6, mediumshuffle, zlib(1)).is_csi=False,
    "A": Index(6, mediumshuffle, zlib(1)).is_csi=False}

In [600]: dfss = pd.DataFrame({"A": ["foo", "bar", "nan"]})

In [601]: dfss
Out[601]:
     A
0  foo
1  bar
2  nan

In [602]: store.append("dfss", dfss)

In [603]: store.select("dfss")
Out[603]:
     A
0  foo
1  bar
2  NaN

# here you need to specify a different nan rep
In [604]: store.append("dfss2", dfss, nan_rep="_nan_")

In [605]: store.select("dfss2")
Out[605]:
     A
0  foo
1  bar
2  nan

In [626]: df = pd.DataFrame({"a": [1, 2], "b": [3, 4]})

In [627]: df.to_parquet("test.parquet", engine="pyarrow")

In [628]: df.to_parquet("test.parquet", index=False)

In [629]: df = pd.DataFrame({"a": [0, 0, 1, 1], "b": [0, 1, 0, 1]})

In [630]: df.to_parquet(path="test", engine="pyarrow", partition_cols=["a"], compression=None)

test
├── a=0
│   ├── 0bac803e32dc42ae83fddfd029cbdebc.parquet
│   └──  ...
└── a=1
    ├── e6ab24a4f45147b49b54a662f0c412a3.parquet
    └── ...

In [641]: import datetime

In [642]: c = ["id", "Date", "Col_1", "Col_2", "Col_3"]

In [643]: d = [
   .....:     (26, datetime.datetime(2010, 10, 18), "X", 27.5, True),
   .....:     (42, datetime.datetime(2010, 10, 19), "Y", -12.5, False),
   .....:     (63, datetime.datetime(2010, 10, 20), "Z", 5.73, True),
   .....: ]
   .....:

In [644]: data = pd.DataFrame(d, columns=c)

In [645]: data
Out[645]:
   id       Date Col_1  Col_2  Col_3
0  26 2010-10-18     X  27.50   True
1  42 2010-10-19     Y -12.50  False
2  63 2010-10-20     Z   5.73   True

In [646]: data.to_sql("data", con=engine)
Out[646]: 3

In [647]: data.to_sql("data_chunked", con=engine, chunksize=1000)
Out[647]: 3

# for roundtripping
with pg_dbapi.connect(uri) as conn:
    df2 = pd.read_sql("pandas_table", conn, dtype_backend="pyarrow")

In [648]: from sqlalchemy.types import String

In [649]: data.to_sql("data_dtype", con=engine, dtype={"Col_1": String})
Out[649]: 3

# Alternative to_sql() *method* for DBs that support COPY FROM
import csv
from io import StringIO

def psql_insert_copy(table, conn, keys, data_iter):
    """
    Execute SQL statement inserting data

    Parameters
    ----------
    table : pandas.io.sql.SQLTable
    conn : sqlalchemy.engine.Engine or sqlalchemy.engine.Connection
    keys : list of str
        Column names
    data_iter : Iterable that iterates the values to be inserted
    """
    # gets a DBAPI connection that can provide a cursor
    dbapi_conn = conn.connection
    with dbapi_conn.cursor() as cur:
        s_buf = StringIO()
        writer = csv.writer(s_buf)
        writer.writerows(data_iter)
        s_buf.seek(0)

        columns = ', '.join(['"{}"'.format(k) for k in keys])
        if table.schema:
            table_name = '{}.{}'.format(table.schema, table.name)
        else:
            table_name = table.name

        sql = 'COPY {} ({}) FROM STDIN WITH CSV'.format(
            table_name, columns)
        cur.copy_expert(sql=sql, file=s_buf)

In [650]: pd.read_sql_table("data", engine)
Out[650]:
   index  id       Date Col_1  Col_2  Col_3
0      0  26 2010-10-18     X  27.50   True
1      1  42 2010-10-19     Y -12.50  False
2      2  63 2010-10-20     Z   5.73   True

In [651]: pd.read_sql_table("data", engine, index_col="id")
Out[651]:
    index       Date Col_1  Col_2  Col_3
id
26      0 2010-10-18     X  27.50   True
42      1 2010-10-19     Y -12.50  False
63      2 2010-10-20     Z   5.73   True

In [652]: pd.read_sql_table("data", engine, columns=["Col_1", "Col_2"])
Out[652]:
  Col_1  Col_2
0     X  27.50
1     Y -12.50
2     Z   5.73

In [653]: pd.read_sql_table("data", engine, parse_dates=["Date"])
Out[653]:
   index  id       Date Col_1  Col_2  Col_3
0      0  26 2010-10-18     X  27.50   True
1      1  42 2010-10-19     Y -12.50  False
2      2  63 2010-10-20     Z   5.73   True

pd.read_sql_table("data", engine, parse_dates={"Date": "%Y-%m-%d"})
pd.read_sql_table(
    "data",
    engine,
    parse_dates={"Date": {"format": "%Y-%m-%d %H:%M:%S"}},
)

df.to_sql(name="table", con=engine, schema="other_schema")
pd.read_sql_table("table", engine, schema="other_schema")

In [654]: pd.read_sql_query("SELECT * FROM data", engine)
Out[654]:
   index  id                        Date Col_1  Col_2  Col_3
0      0  26  2010-10-18 00:00:00.000000     X  27.50      1
1      1  42  2010-10-19 00:00:00.000000     Y -12.50      0
2      2  63  2010-10-20 00:00:00.000000     Z   5.73      1

In [655]: pd.read_sql_query("SELECT id, Col_1, Col_2 FROM data WHERE id = 42;", engine)
Out[655]:
   id Col_1  Col_2
0  42     Y  -12.5

In [656]: df = pd.DataFrame(np.random.randn(20, 3), columns=list("abc"))

In [657]: df.to_sql(name="data_chunks", con=engine, index=False)
Out[657]: 20

In [658]: for chunk in pd.read_sql_query("SELECT * FROM data_chunks", engine, chunksize=5):
   .....:     print(chunk)
   .....:
          a         b         c
0 -0.395347 -0.822726 -0.363777
1  1.676124 -0.908102 -1.391346
2 -1.094269  0.278380  1.205899
3  1.503443  0.932171 -0.709459
4 -0.645944 -1.351389  0.132023
          a         b         c
0  0.210427  0.192202  0.661949
1  1.690629 -1.046044  0.618697
2 -0.013863  1.314289  1.951611
3 -1.485026  0.304662  1.194757
4 -0.446717  0.528496 -0.657575
          a         b         c
0 -0.876654  0.336252  0.172668
1  0.337684 -0.411202 -0.828394
2 -0.244413  1.094948  0.087183
3  1.125934 -1.480095  1.205944
4 -0.451849  0.452214 -2.208192
          a         b         c
0 -2.061019  0.044184 -0.017118
1  1.248959 -0.675595 -1.908296
2 -0.125934  1.491974  0.648726
3  0.391214  0.438609  1.634248
4  1.208707 -1.535740  1.620399

from sqlalchemy import create_engine

engine = create_engine("postgresql://scott:tiger@localhost:5432/mydatabase")

engine = create_engine("mysql+mysqldb://scott:tiger@localhost/foo")

engine = create_engine("oracle://scott:[email protected]:1521/sidname")

engine = create_engine("mssql+pyodbc://mydsn")

# sqlite://<nohostname>/<path>
# where <path> is relative:
engine = create_engine("sqlite:///foo.db")

# or absolute, starting with a slash:
engine = create_engine("sqlite:////absolute/path/to/foo.db")

In [659]: import sqlalchemy as sa

In [660]: pd.read_sql(
   .....:     sa.text("SELECT * FROM data where Col_1=:col1"), engine, params={"col1": "X"}
   .....: )
   .....:
Out[660]:
   index  id                        Date Col_1  Col_2  Col_3
0      0  26  2010-10-18 00:00:00.000000     X   27.5      1

In [661]: metadata = sa.MetaData()

In [662]: data_table = sa.Table(
   .....:     "data",
   .....:     metadata,
   .....:     sa.Column("index", sa.Integer),
   .....:     sa.Column("Date", sa.DateTime),
   .....:     sa.Column("Col_1", sa.String),
   .....:     sa.Column("Col_2", sa.Float),
   .....:     sa.Column("Col_3", sa.Boolean),
   .....: )
   .....:

In [663]: pd.read_sql(sa.select(data_table).where(data_table.c.Col_3 is True), engine)
Out[663]:
Empty DataFrame
Columns: [index, Date, Col_1, Col_2, Col_3]
Index: []

In [664]: import datetime as dt

In [665]: expr = sa.select(data_table).where(data_table.c.Date > sa.bindparam("date"))

In [666]: pd.read_sql(expr, engine, params={"date": dt.datetime(2010, 10, 18)})
Out[666]:
   index       Date Col_1  Col_2  Col_3
0      1 2010-10-19     Y -12.50  False
1      2 2010-10-20     Z   5.73   True

import sqlite3

con = sqlite3.connect(":memory:")

data.to_sql("data", con)
pd.read_sql_query("SELECT * FROM data", con)

In [667]: df = pd.DataFrame(np.random.randn(10, 2), columns=list("AB"))

In [668]: df.to_stata("stata.dta")