Machine Learning With Python 简明教程

$ ruby -e "$(curl -fsSL
https://raw.githubusercontent.com/Homebrew/install/master/install)"

$ brew update

$ brew install python3

C:\>jupyter notebook

pip install jupyter

import numpy as np

pip install NumPy

import pandas as pd

pip install Pandas

In [1]: import pandas as pd

In [2]: import numpy as np

In [3]: data = np.array(['g','a','u','r','a','v'])

In [4]: s = pd.Series(data)

In [5]: print (s)

0 g
1 a
2 u
3 r
4 a
5 v

dtype: object

from sklearn.datasets import load_breast_cancer

pip install -U scikit-learn

import csv

import numpy as np

path = r"c:\iris.csv"

with open(path,'r') as f:
   reader = csv.reader(f,delimiter = ',')
   headers = next(reader)
   data = list(reader)
   data = np.array(data).astype(float)

print(headers)

print(data.shape)

print(data[:3])

['sepal_length', 'sepal_width', 'petal_length', 'petal_width']
(150, 4)
[  [5.1 3.5 1.4 0.2]
   [4.9 3. 1.4 0.2]
   [4.7 3.2 1.3 0.2]]

from numpy import loadtxt
path = r"C:\pima-indians-diabetes.csv"
datapath= open(path, 'r')
data = loadtxt(datapath, delimiter=",")
print(data.shape)
print(data[:3])

(768, 9)
[  [ 6. 148. 72. 35. 0. 33.6 0.627 50. 1.]
   [ 1. 85. 66. 29. 0. 26.6 0.351 31. 0.]
   [ 8. 183. 64. 0. 0. 23.3 0.672 32. 1.]]

from pandas import read_csv
path = r"C:\iris.csv"
data = read_csv(path)
print(data.shape)
print(data[:3])

Output:

(150, 4)
   sepal_length   sepal_width  petal_length   petal_width
0         5.1     3.5          1.4            0.2
1         4.9     3.0          1.4            0.2
2         4.7     3.2          1.3            0.2

from pandas import read_csv
path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
print(data.shape)
print(data[:3])

(768, 9)
   preg  plas  pres   skin  test   mass    pedi    age   class
0   6    148    72      35    0     33.6   0.627    50      1
1   1    85     66      29    0     26.6   0.351    31      0
2   8    183    64      0     0     23.3   0.672    32      1

from pandas import read_csv
path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
print(data.head(50))

preg   plas  pres    skin  test  mass   pedi    age      class
0      6      148     72     35   0     33.6    0.627    50    1
1      1       85     66     29   0     26.6    0.351    31    0
2      8      183     64      0   0     23.3    0.672    32    1
3      1       89     66     23  94     28.1    0.167    21    0
4      0      137     40     35  168    43.1    2.288    33    1
5      5      116     74      0   0     25.6    0.201    30    0
6      3       78     50     32   88    31.0    0.248    26    1
7     10      115      0      0   0     35.3    0.134    29    0
8      2      197     70     45  543    30.5    0.158    53    1
9      8      125     96      0   0     0.0     0.232    54    1
10     4      110     92      0   0     37.6    0.191    30    0
11    10      168     74      0   0     38.0    0.537    34    1
12    10      139     80      0   0     27.1    1.441    57    0
13     1      189     60     23  846    30.1    0.398    59    1
14     5      166     72     19  175    25.8    0.587    51    1
15     7      100      0      0   0     30.0    0.484    32    1
16     0      118     84     47  230    45.8    0.551    31    1
17     7      107     74      0   0     29.6    0.254    31    1
18     1      103     30     38  83     43.3    0.183    33    0
19     1      115     70     30  96     34.6    0.529    32    1
20     3      126     88     41  235    39.3    0.704    27    0
21     8       99     84      0   0     35.4    0.388    50    0
22     7      196     90      0   0     39.8    0.451    41    1
23     9      119     80     35   0     29.0    0.263    29    1
24    11      143     94     33  146    36.6    0.254    51    1
25    10      125     70     26  115    31.1    0.205    41    1
26     7      147     76      0   0     39.4    0.257    43    1
27     1       97     66     15  140    23.2    0.487    22    0
28    13      145     82     19  110    22.2    0.245    57    0
29     5      117     92      0   0     34.1    0.337    38    0
30     5      109     75     26   0     36.0    0.546    60    0
31     3      158     76     36  245    31.6    0.851    28    1
32     3       88     58     11   54    24.8    0.267    22    0
33     6       92     92      0   0     19.9    0.188    28    0
34    10      122     78     31   0     27.6    0.512    45    0
35     4      103     60     33  192    24.0    0.966    33    0
36    11      138     76      0   0     33.2    0.420    35    0
37     9      102     76     37   0     32.9    0.665    46    1
38     2       90     68     42   0     38.2    0.503    27    1
39     4      111     72     47  207    37.1    1.390    56    1
40     3      180     64     25   70    34.0    0.271    26    0
41     7      133     84      0   0     40.2    0.696    37    0
42     7      106     92     18   0     22.7    0.235    48    0
43     9      171    110     24  240    45.4    0.721    54    1
44     7      159     64      0   0     27.4    0.294    40    0
45     0      180     66     39   0     42.0    1.893    25    1
46     1      146     56      0   0     29.7    0.564    29    0
47     2       71     70     27   0     28.0    0.586    22    0
48     7      103     66     32   0     39.1    0.344    31    1
49     7      105      0      0   0     0.0     0.305    24    0

from pandas import read_csv
path = r"C:\iris.csv"
data = read_csv(path)
print(data.shape)

(150, 4)

from pandas import read_csv
path = r"C:\iris.csv"
data = read_csv(path)
print(data.dtypes)

sepal_length float64
sepal_width float64
petal_length float64
petal_width float64
dtype: object

from pandas import read_csv
from pandas import set_option
path = r"C:\pima-indians-diabetes.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=names)
set_option('display.width', 100)
set_option('precision', 2)
print(data.shape)
print(data.describe())

(768, 9)
         preg      plas       pres      skin      test        mass       pedi      age      class
count 768.00      768.00    768.00     768.00    768.00     768.00     768.00    768.00    768.00
mean    3.85      120.89     69.11      20.54     79.80      31.99       0.47     33.24      0.35
std     3.37       31.97     19.36      15.95    115.24       7.88       0.33     11.76      0.48
min     0.00        0.00      0.00       0.00      0.00       0.00       0.08     21.00      0.00
25%     1.00       99.00     62.00       0.00      0.00      27.30       0.24     24.00      0.00
50%     3.00      117.00     72.00      23.00     30.50      32.00       0.37     29.00      0.00
75%     6.00      140.25     80.00      32.00    127.25      36.60       0.63     41.00      1.00
max    17.00      199.00    122.00      99.00    846.00      67.10       2.42     81.00      1.00

from pandas import read_csv
path = r"C:\pima-indians-diabetes.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=names)
count_class = data.groupby('class').size()
print(count_class)

Class
0 500
1 268
dtype: int64

from pandas import read_csv
from pandas import set_option
path = r"C:\pima-indians-diabetes.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=names)
set_option('display.width', 100)
set_option('precision', 2)
correlations = data.corr(method='pearson')
print(correlations)

preg     plas     pres     skin     test      mass     pedi       age      class
preg     1.00     0.13     0.14     -0.08     -0.07   0.02     -0.03       0.54   0.22
plas     0.13     1.00     0.15     0.06       0.33   0.22      0.14       0.26   0.47
pres     0.14     0.15     1.00     0.21       0.09   0.28      0.04       0.24   0.07
skin    -0.08     0.06     0.21     1.00       0.44   0.39      0.18      -0.11   0.07
test    -0.07     0.33     0.09     0.44       1.00   0.20      0.19      -0.04   0.13
mass     0.02     0.22     0.28     0.39       0.20   1.00      0.14       0.04   0.29
pedi    -0.03     0.14     0.04     0.18       0.19   0.14      1.00       0.03   0.17
age      0.54     0.26     0.24     -0.11     -0.04   0.04      0.03       1.00   0.24
class    0.22     0.47     0.07     0.07       0.13   0.29      0.17       0.24   1.00

from pandas import read_csv
path = r"C:\pima-indians-diabetes.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=names)
print(data.skew())

preg   0.90
plas   0.17
pres  -1.84
skin   0.11
test   2.27
mass  -0.43
pedi   1.92
age    1.13
class  0.64
dtype: float64

from matplotlib import pyplot
from pandas import read_csv
path = r"C:\pima-indians-diabetes.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=names)
data.hist()
pyplot.show()

from matplotlib import pyplot
from pandas import read_csv
path = r"C:\pima-indians-diabetes.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=names)
data.plot(kind='density', subplots=True, layout=(3,3), sharex=False)
pyplot.show()

from matplotlib import pyplot
from pandas import read_csv
path = r"C:\pima-indians-diabetes.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=names)
data.plot(kind='box', subplots=True, layout=(3,3), sharex=False,sharey=False)
pyplot.show()

from matplotlib import pyplot
from pandas import read_csv
import numpy
Path = r"C:\pima-indians-diabetes.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(Path, names=names)
correlations = data.corr()
fig = pyplot.figure()
ax = fig.add_subplot(111)
cax = ax.matshow(correlations, vmin=-1, vmax=1)
fig.colorbar(cax)
ticks = numpy.arange(0,9,1)
ax.set_xticks(ticks)
ax.set_yticks(ticks)
ax.set_xticklabels(names)
ax.set_yticklabels(names)
pyplot.show()

from matplotlib import pyplot
from pandas import read_csv
from pandas.tools.plotting import scatter_matrix
path = r"C:\pima-indians-diabetes.csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=names)
scatter_matrix(data)
pyplot.show()

from pandas import read_csv
from numpy import set_printoptions
from sklearn import preprocessing
path = r'C:\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(path, names=names)
array = dataframe.values

data_scaler = preprocessing.MinMaxScaler(feature_range=(0,1))
data_rescaled = data_scaler.fit_transform(array)

set_printoptions(precision=1)
print ("\nScaled data:\n", data_rescaled[0:10])

Scaled data:
[[0.4 0.7 0.6 0.4 0. 0.5 0.2 0.5 1. ]
[0.1 0.4 0.5 0.3 0. 0.4 0.1 0.2 0. ]
[0.5 0.9 0.5 0. 0. 0.3 0.3 0.2 1. ]
[0.1 0.4 0.5 0.2 0.1 0.4 0. 0. 0. ]
[0. 0.7 0.3 0.4 0.2 0.6 0.9 0.2 1. ]
[0.3 0.6 0.6 0. 0. 0.4 0.1 0.2 0. ]
[0.2 0.4 0.4 0.3 0.1 0.5 0.1 0.1 1. ]
[0.6 0.6 0. 0. 0. 0.5 0. 0.1 0. ]
[0.1 1. 0.6 0.5 0.6 0.5 0. 0.5 1. ]
[0.5 0.6 0.8 0. 0. 0. 0.1 0.6 1. ]]

from pandas import read_csv
from numpy import set_printoptions
from sklearn.preprocessing import Normalizer
path = r'C:\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv (path, names=names)
array = dataframe.values

Data_normalizer = Normalizer(norm='l1').fit(array)
Data_normalized = Data_normalizer.transform(array)

set_printoptions(precision=2)
print ("\nNormalized data:\n", Data_normalized [0:3])

Normalized data:
[[0.02 0.43 0.21 0.1 0. 0.1 0. 0.14 0. ]
[0. 0.36 0.28 0.12 0. 0.11 0. 0.13 0. ]
[0.03 0.59 0.21 0. 0. 0.07 0. 0.1 0. ]]

from pandas import read_csv
from numpy import set_printoptions
from sklearn.preprocessing import Normalizer
path = r'C:\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv (path, names=names)
array = dataframe.values

Data_normalizer = Normalizer(norm='l2').fit(array)
Data_normalized = Data_normalizer.transform(array)

set_printoptions(precision=2)
print ("\nNormalized data:\n", Data_normalized [0:3])

Normalized data:
[[0.03 0.83 0.4 0.2 0. 0.19 0. 0.28 0.01]
[0.01 0.72 0.56 0.24 0. 0.22 0. 0.26 0. ]
[0.04 0.92 0.32 0. 0. 0.12 0. 0.16 0.01]]

from pandas import read_csv
from sklearn.preprocessing import Binarizer
path = r'C:\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(path, names=names)
array = dataframe.values

binarizer = Binarizer(threshold=0.5).fit(array)
Data_binarized = binarizer.transform(array)

print ("\nBinary data:\n", Data_binarized [0:5])

Binary data:
[[1. 1. 1. 1. 0. 1. 1. 1. 1.]
[1. 1. 1. 1. 0. 1. 0. 1. 0.]
[1. 1. 1. 0. 0. 1. 1. 1. 1.]
[1. 1. 1. 1. 1. 1. 0. 1. 0.]
[0. 1. 1. 1. 1. 1. 1. 1. 1.]]

from sklearn.preprocessing import StandardScaler
from pandas import read_csv
from numpy import set_printoptions
path = r'C:\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(path, names=names)
array = dataframe.values

data_scaler = StandardScaler().fit(array)
data_rescaled = data_scaler.transform(array)

set_printoptions(precision=2)
print ("\nRescaled data:\n", data_rescaled [0:5])

Rescaled data:
[[ 0.64 0.85 0.15 0.91 -0.69 0.2 0.47 1.43 1.37]
[-0.84 -1.12 -0.16 0.53 -0.69 -0.68 -0.37 -0.19 -0.73]
[ 1.23 1.94 -0.26 -1.29 -0.69 -1.1 0.6 -0.11 1.37]
[-0.84 -1. -0.16 0.15 0.12 -0.49 -0.92 -1.04 -0.73]
[-1.14 0.5 -1.5 0.91 0.77 1.41 5.48 -0.02 1.37]]

import numpy as np
from sklearn import preprocessing

input_labels = ['red','black','red','green','black','yellow','white']

encoder = preprocessing.LabelEncoder()
encoder.fit(input_labels)

test_labels = ['green','red','black']
encoded_values = encoder.transform(test_labels)
print("\nLabels =", test_labels)
print("Encoded values =", list(encoded_values))
encoded_values = [3,0,4,1]
decoded_list = encoder.inverse_transform(encoded_values)

print("\nEncoded values =", encoded_values)
print("\nDecoded labels =", list(decoded_list))

Labels = ['green', 'red', 'black']
Encoded values = [1, 2, 0]
Encoded values = [3, 0, 4, 1]
Decoded labels = ['white', 'black', 'yellow', 'green']

from pandas import read_csv
from numpy import set_printoptions
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
path = r'C:\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(path, names=names)
array = dataframe.values

X = array[:,0:8]
Y = array[:,8]

test = SelectKBest(score_func=chi2, k=4)
fit = test.fit(X,Y)

set_printoptions(precision=2)
print(fit.scores_)
featured_data = fit.transform(X)
print ("\nFeatured data:\n", featured_data[0:4])

[ 111.52 1411.89 17.61 53.11 2175.57 127.67 5.39 181.3 ]
Featured data:
[[148. 0. 33.6 50. ]
[ 85. 0. 26.6 31. ]
[183. 0. 23.3 32. ]
[ 89. 94. 28.1 21. ]]

from pandas import read_csv
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
path = r'C:\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(path, names=names)
array = dataframe.values

X = array[:,0:8]
Y = array[:,8]

model = LogisticRegression()
rfe = RFE(model, 3)
fit = rfe.fit(X, Y)
print("Number of Features: %d")
print("Selected Features: %s")
print("Feature Ranking: %s")

Number of Features: 3
Selected Features: [ True False False False False True True False]
Feature Ranking: [1 2 3 5 6 1 1 4]

from pandas import read_csv
from sklearn.decomposition import PCA
path = r'C:\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(path, names=names)
array = dataframe.values

X = array[:,0:8]
Y = array[:,8]

pca = PCA(n_components=3)
fit = pca.fit(X)
print("Explained Variance: %s") % fit.explained_variance_ratio_
print(fit.components_)

Explained Variance: [ 0.88854663 0.06159078 0.02579012]
[[ -2.02176587e-03 9.78115765e-02 1.60930503e-02 6.07566861e-02
9.93110844e-01 1.40108085e-02 5.37167919e-04 -3.56474430e-03]
[ 2.26488861e-02 9.72210040e-01 1.41909330e-01 -5.78614699e-02
-9.46266913e-02 4.69729766e-02 8.16804621e-04 1.40168181e-01]
[ -2.24649003e-02 1.43428710e-01 -9.22467192e-01 -3.07013055e-01
2.09773019e-02 -1.32444542e-01 -6.39983017e-04 -1.25454310e-01]]

from pandas import read_csv
from sklearn.ensemble import ExtraTreesClassifier
path = r'C:\Desktop\pima-indians-diabetes.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(data, names=names)
array = dataframe.values

X = array[:,0:8]
Y = array[:,8]

model = ExtraTreesClassifier()
model.fit(X, Y)
print(model.feature_importances_)

[ 0.11070069 0.2213717 0.08824115 0.08068703 0.07281761 0.14548537 0.12654214 0.15415431]

import sklearn

from sklearn.datasets import load_breast_cancer

data = load_breast_cancer()

label_names = data['target_names']
   labels = data['target']
   feature_names = data['feature_names']
   features = data['data']

print(label_names)

['malignant' 'benign']

print(feature_names[0])

mean radius

print(feature_names[1])

mean texture

print(features[0])

[1.799e+01 1.038e+01 1.228e+02 1.001e+03 1.184e-01 2.776e-01 3.001e-01
1.471e-01 2.419e-01 7.871e-02 1.095e+00 9.053e-01 8.589e+00 1.534e+02
6.399e-03 4.904e-02 5.373e-02 1.587e-02 3.003e-02 6.193e-03 2.538e+01
1.733e+01 1.846e+02 2.019e+03 1.622e-01 6.656e-01 7.119e-01 2.654e-01
4.601e-01 1.189e-01]

print(features[1])

[2.057e+01 1.777e+01 1.329e+02 1.326e+03 8.474e-02 7.864e-02 8.690e-02
7.017e-02 1.812e-01 5.667e-02 5.435e-01 7.339e-01 3.398e+00 7.408e+01
5.225e-03 1.308e-02 1.860e-02 1.340e-02 1.389e-02 3.532e-03 2.499e+01
2.341e+01 1.588e+02 1.956e+03 1.238e-01 1.866e-01 2.416e-01 1.860e-01
2.750e-01 8.902e-02]

from sklearn.model_selection import train_test_split

train, test, train_labels, test_labels = train_test_split(features,labels,test_size = 0.40, random_state = 42)

from sklearn.naive_bayes import GaussianNB

gnb = GaussianNB()

model = gnb.fit(train, train_labels)

preds = gnb.predict(test)
print(preds)

[1 0 0 1 1 0 0 0 1 1 1 0 1 0 1 0 1 1 1 0 1 1 0 1 1 1 1 1 1 0 1 1 1 1 1 1 0
1 0 1 1 0 1 1 1 1 1 1 1 1 0 0 1 1 1 1 1 0 0 1 1 0 0 1 1 1 0 0 1 1 0 0 1 0
1 1 1 1 1 1 0 1 1 0 0 0 0 0 1 1 1 1 1 1 1 1 0 0 1 0 0 1 0 0 1 1 1 0 1 1 0
1 1 0 0 0 1 1 1 0 0 1 1 0 1 0 0 1 1 0 0 0 1 1 1 0 1 1 0 0 1 0 1 1 0 1 0 0
1 1 1 1 1 1 1 0 0 1 1 1 1 1 1 1 1 1 1 1 1 0 1 1 1 0 1 1 0 1 1 1 1 1 1 0 0
0 1 1 0 1 0 1 1 1 1 0 1 1 0 1 1 1 0 1 0 0 1 1 1 1 1 1 1 1 0 1 1 1 1 1 0 1
0 0 1 1 0 1]

from sklearn.metrics import accuracy_score
   print(accuracy_score(test_labels,preds))
   0.951754385965

[[ 73 7]
[ 4 144]]

Accuracy of Logistic Regression model is: 95.6884561891516

import pandas as pd
import numpy as np
from sklearn import svm, datasets
import matplotlib.pyplot as plt

iris = datasets.load_iris()

X = iris.data[:, :2]
y = iris.target

x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
h = (x_max / x_min)/100
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
   np.arange(y_min, y_max, h))
X_plot = np.c_[xx.ravel(), yy.ravel()]

C = 1.0

Z = svc_classifier.predict(X_plot)
Z = Z.reshape(xx.shape)
plt.figure(figsize=(15, 5))
plt.subplot(121)
plt.contourf(xx, yy, Z, cmap=plt.cm.tab10, alpha=0.3)
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Set1)
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.xlim(xx.min(), xx.max())
plt.title('Support Vector Classifier with linear kernel')

Text(0.5, 1.0, 'Support Vector Classifier with linear kernel')

Svc_classifier = svm.SVC(kernel='rbf', gamma =‘auto’,C=C).fit(X, y)
Z = svc_classifier.predict(X_plot)
Z = Z.reshape(xx.shape)
plt.figure(figsize=(15, 5))
plt.subplot(121)
plt.contourf(xx, yy, Z, cmap=plt.cm.tab10, alpha=0.3)
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Set1)
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.xlim(xx.min(), xx.max())
plt.title('Support Vector Classifier with rbf kernel')

Text(0.5, 1.0, 'Support Vector Classifier with rbf kernel')

import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split

col_names = ['pregnant', 'glucose', 'bp', 'skin', 'insulin', 'bmi', 'pedigree', 'age', 'label']
pima = pd.read_csv(r"C:\pima-indians-diabetes.csv", header=None, names=col_names)
pima.head()

      pregnant    glucose  bp    skin  insulin  bmi   pedigree    age   label
0       6         148      72    35     0       33.6    0.627     50      1
1       1         85       66    29     0       26.6    0.351     31      0
2       8         183      64     0     0       23.3    0.672     32      1
3       1         89       66    23     94      28.1    0.167     21      0
4       0         137      40    35     168     43.1    2.288     33      1

feature_cols = ['pregnant', 'insulin', 'bmi', 'age','glucose','bp','pedigree']
X = pima[feature_cols] # Features
y = pima.label # Target variable

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=1)

clf = DecisionTreeClassifier()
clf = clf.fit(X_train,y_train)

y_pred = clf.predict(X_test)

from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
result = confusion_matrix(y_test, y_pred)
print("Confusion Matrix:")
print(result)
result1 = classification_report(y_test, y_pred)
print("Classification Report:",)
print (result1)
result2 = accuracy_score(y_test,y_pred)
print("Accuracy:",result2)

Confusion Matrix:
[[116 30]
[ 46 39]]
Classification Report:
            precision   recall   f1-score    support
      0       0.72      0.79       0.75     146
      1       0.57      0.46       0.51     85
micro avg     0.67      0.67       0.67     231
macro avg     0.64      0.63       0.63     231
weighted avg  0.66      0.67       0.66     231

Accuracy: 0.670995670995671

from sklearn.tree import export_graphviz
from sklearn.externals.six import StringIO
from IPython.display import Image
import pydotplus

dot_data = StringIO()
export_graphviz(clf, out_file=dot_data,
      filled=True, rounded=True,
      special_characters=True,feature_names = feature_cols,class_names=['0','1'])
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
graph.write_png('Pima_diabetes_Tree.png')
Image(graph.create_png())

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()

from sklearn.datasets import make_blobs
X, y = make_blobs(300, 2, centers=2, random_state=2, cluster_std=1.5)
plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='summer');

from sklearn.naive_bayes import GaussianNB
model_GBN = GaussianNB()
model_GNB.fit(X, y);

rng = np.random.RandomState(0)
Xnew = [-6, -14] + [14, 18] * rng.rand(2000, 2)
ynew = model_GNB.predict(Xnew)

plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='summer')
lim = plt.axis()
plt.scatter(Xnew[:, 0], Xnew[:, 1], c=ynew, s=20, cmap='summer', alpha=0.1)
plt.axis(lim);

yprob = model_GNB.predict_proba(Xnew)
yprob[-10:].round(3)

array([[0.998, 0.002],
      [1. , 0. ],
      [0.987, 0.013],
      [1. , 0. ],
      [1. , 0. ],
      [1. , 0. ],
      [1. , 0. ],
      [1. , 0. ],
      [0. , 1. ],
      [0.986, 0.014]])

Confusion Matrix:
[[14 0 0]
[ 0 18 1]
[ 0 0 12]]
Classification Report:
               precision       recall     f1-score       support
Iris-setosa        1.00         1.00        1.00         14
Iris-versicolor    1.00         0.95        0.97         19
Iris-virginica     0.92         1.00        0.96         12
micro avg          0.98         0.98        0.98         45
macro avg          0.97         0.98        0.98         45
weighted avg       0.98         0.98        0.98         45

Accuracy: 0.9777777777777777

import numpy as np
from sklearn import linear_model
import sklearn.metrics as sm
import matplotlib.pyplot as plt

input = r'C:\linear.txt'

input_data = np.loadtxt(input, delimiter=',')
X, y = input_data[:, :-1], input_data[:, -1]

training_samples = int(0.6 * len(X))
testing_samples = len(X) - num_training

X_train, y_train = X[:training_samples], y[:training_samples]

X_test, y_test = X[training_samples:], y[training_samples:]

reg_linear= linear_model.LinearRegression()

reg_linear.fit(X_train, y_train)

y_test_pred = reg_linear.predict(X_test)

plt.scatter(X_test, y_test, color='red')
plt.plot(X_test, y_test_pred, color='black', linewidth=2)
plt.xticks(())
plt.yticks(())
plt.show()

print("Regressor model performance:")
print("Mean absolute error(MAE) =", round(sm.mean_absolute_error(y_test, y_test_pred), 2))
print("Mean squared error(MSE) =", round(sm.mean_squared_error(y_test, y_test_pred), 2))
print("Median absolute error =", round(sm.median_absolute_error(y_test, y_test_pred), 2))
print("Explain variance score =", round(sm.explained_variance_score(y_test, y_test_pred), 2))
print("R2 score =", round(sm.r2_score(y_test, y_test_pred), 2))

Regressor model performance:
Mean absolute error(MAE) = 1.78
Mean squared error(MSE) = 3.89
Median absolute error = 2.01
Explain variance score = -0.09
R2 score = -0.09

%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt

def coef_estimation(x, y):

n = np.size(x)

m_x, m_y = np.mean(x), np.mean(y)

SS_xy = np.sum(y*x) - n*m_y*m_x
SS_xx = np.sum(x*x) - n*m_x*m_x

b_1 = SS_xy / SS_xx
b_0 = m_y - b_1*m_x
return(b_0, b_1)

def plot_regression_line(x, y, b):

plt.scatter(x, y, color = "m", marker = "o", s = 30)

y_pred = b[0] + b[1]*x

plt.plot(x, y_pred, color = "g")
plt.xlabel('x')
plt.ylabel('y')
plt.show()

def main():
   x = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
   y = np.array([100, 300, 350, 500, 750, 800, 850, 900, 1050, 1250])
   b = coef_estimation(x, y)
   print("Estimated coefficients:\nb_0 = {} \nb_1 = {}".format(b[0], b[1]))
   plot_regression_line(x, y, b)

if __name__ == "__main__":
main()

Estimated coefficients:
b_0 = 154.5454545454545
b_1 = 117.87878787878788

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets, linear_model
from sklearn.metrics import mean_squared_error, r2_score

diabetes = datasets.load_diabetes()

X = diabetes.data[:, np.newaxis, 2]

X_train = X[:-30]
X_test = X[-30:]

y_train = diabetes.target[:-30]
y_test = diabetes.target[-30:]

regr = linear_model.LinearRegression()

regr.fit(X_train, y_train)

y_pred = regr.predict(X_test)

print('Coefficients: \n', regr.coef_)
print("Mean squared error: %.2f"
   % mean_squared_error(y_test, y_pred))
print('Variance score: %.2f' % r2_score(y_test, y_pred))

plt.scatter(X_test, y_test, color='blue')
plt.plot(X_test, y_pred, color='red', linewidth=3)
plt.xticks(())
plt.yticks(())
plt.show()

Coefficients:
   [941.43097333]
Mean squared error: 3035.06
Variance score: 0.41

Coefficients:
[-1.16358797e-01 6.44549228e-02 1.65416147e-01 1.45101654e+00
-1.77862563e+01 2.80392779e+00 4.61905315e-02 -1.13518865e+00
3.31725870e-01 -1.01196059e-02 -9.94812678e-01 9.18522056e-03
-7.92395217e-01]
Variance score: 0.709454060230326

%matplotlib inline
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
import numpy as np
from sklearn.cluster import KMeans

from sklearn.datasets.samples_generator import make_blobs
X, y_true = make_blobs(n_samples=400, centers=4, cluster_std=0.60, random_state=0)

plt.scatter(X[:, 0], X[:, 1], s=20);
plt.show()

kmeans = KMeans(n_clusters=4)
kmeans.fit(X)
y_kmeans = kmeans.predict(X)

plt.scatter(X[:, 0], X[:, 1], c=y_kmeans, s=20, cmap='summer')
centers = kmeans.cluster_centers_
plt.scatter(centers[:, 0], centers[:, 1], c='blue', s=100, alpha=0.9);
plt.show()

%matplotlib inline
import matplotlib.pyplot as plt
import seaborn as sns; sns.set()
import numpy as np
from sklearn.cluster import KMeans

from sklearn.datasets import load_digits
digits = load_digits()
digits.data.shape

(1797, 64)

kmeans = KMeans(n_clusters=10, random_state=0)
clusters = kmeans.fit_predict(digits.data)
kmeans.cluster_centers_.shape

(10, 64)

fig, ax = plt.subplots(2, 5, figsize=(8, 3))
centers = kmeans.cluster_centers_.reshape(10, 8, 8)
for axi, center in zip(ax.flat, centers):
   axi.set(xticks=[], yticks=[])
   axi.imshow(center, interpolation='nearest', cmap=plt.cm.binary)

from scipy.stats import mode
labels = np.zeros_like(clusters)
for i in range(10):
   mask = (clusters == i)
   labels[mask] = mode(digits.target[mask])[0]

from sklearn.metrics import accuracy_score
accuracy_score(digits.target, labels)

0.7935447968836951

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np

X = np.array([[7,8],[12,20],[17,19],[26,15],[32,37],[87,75],[73,85], [62,80],[73,60],[87,96],])
labels = range(1, 11)
plt.figure(figsize=(10, 7))
plt.subplots_adjust(bottom=0.1)
plt.scatter(X[:,0],X[:,1], label='True Position')
for label, x, y in zip(labels, X[:, 0], X[:, 1]):
   plt.annotate(label,xy=(x, y), xytext=(-3, 3),textcoords='offset points', ha='right', va='bottom')
plt.show()

from scipy.cluster.hierarchy import dendrogram, linkage
from matplotlib import pyplot as plt
linked = linkage(X, 'single')
labelList = range(1, 11)
plt.figure(figsize=(10, 7))
dendrogram(linked, orientation='top',labels=labelList, distance_sort='descending',show_leaf_counts=True)
plt.show()

from sklearn.cluster import AgglomerativeClustering
cluster = AgglomerativeClustering(n_clusters=2, affinity='euclidean', linkage='ward')
cluster.fit_predict(X)

plt.scatter(X[:,0],X[:,1], c=cluster.labels_, cmap='rainbow')

import matplotlib.pyplot as plt
import pandas as pd
%matplotlib inline
import numpy as np
from pandas import read_csv
path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
array = data.values
X = array[:,0:8]
Y = array[:,8]
data.shape
(768, 9)
data.head()

patient_data = data.iloc[:, 3:5].values
import scipy.cluster.hierarchy as shc
plt.figure(figsize=(10, 7))
plt.title("Patient Dendograms")
dend = shc.dendrogram(shc.linkage(data, method='ward'))

from sklearn.cluster import AgglomerativeClustering
cluster = AgglomerativeClustering(n_clusters=4, affinity='euclidean', linkage='ward')
cluster.fit_predict(patient_data)
plt.figure(figsize=(10, 7))
plt.scatter(patient_data[:,0], patient_data[:,1], c=cluster.labels_, cmap='rainbow')

Confusion Matrix:
[[21 0 0]
[ 0 16 0]
[ 0 7 16]]
Classification Report:
            precision      recall       f1-score       support
Iris-setosa       1.00        1.00         1.00          21
Iris-versicolor   0.70        1.00         0.82          16
Iris-virginica    1.00        0.70         0.82          23
micro avg         0.88        0.88         0.88          60
macro avg         0.90        0.90         0.88          60
weighted avg      0.92        0.88         0.88          60


Accuracy: 0.8833333333333333

The MSE is: 0.12226666666666669

from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
from sklearn.metrics import roc_auc_score
from sklearn.metrics import log_loss
X_actual = [1, 1, 0, 1, 0, 0, 1, 0, 0, 0]
Y_predic = [1, 0, 1, 1, 1, 0, 1, 1, 0, 0]
results = confusion_matrix(X_actual, Y_predic)
print ('Confusion Matrix :')
print(results)
print ('Accuracy Score is',accuracy_score(X_actual, Y_predic))
print ('Classification Report : ')
print (classification_report(X_actual, Y_predic))
print('AUC-ROC:',roc_auc_score(X_actual, Y_predic))
print('LOGLOSS Value is',log_loss(X_actual, Y_predic))

Confusion Matrix :
[[3 3]
[1 3]]
Accuracy Score is 0.6
Classification Report :
            precision      recall      f1-score       support
      0       0.75          0.50      0.60           6
      1       0.50          0.75      0.60           4
micro avg     0.60          0.60      0.60           10
macro avg     0.62          0.62      0.60           10
weighted avg  0.65          0.60      0.60           10
AUC-ROC:  0.625
LOGLOSS Value is 13.815750437193334

from sklearn.metrics import r2_score
from sklearn.metrics import mean_absolute_error
from sklearn.metrics import mean_squared_error
X_actual = [5, -1, 2, 10]
Y_predic = [3.5, -0.9, 2, 9.9]
print ('R Squared =',r2_score(X_actual, Y_predic))
print ('MAE =',mean_absolute_error(X_actual, Y_predic))
print ('MSE =',mean_squared_error(X_actual, Y_predic))

R Squared = 0.9656060606060606
MAE = 0.42499999999999993
MSE = 0.5674999999999999

0.7790148448043184

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.pipeline import Pipeline
from sklearn.pipeline import FeatureUnion
from sklearn.linear_model import LogisticRegression
from sklearn.decomposition import PCA
from sklearn.feature_selection import SelectKBest

path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
array = data.values

features = []
features.append(('pca', PCA(n_components=3)))
features.append(('select_best', SelectKBest(k=6)))
feature_union = FeatureUnion(features)

estimators = []
estimators.append(('feature_union', feature_union))
estimators.append(('logistic', LogisticRegression()))
model = Pipeline(estimators)

kfold = KFold(n_splits=20, random_state=7)
results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())

0.7789811066126855

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier

path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
array = data.values
X = array[:,0:8]
Y = array[:,8]

seed = 7
kfold = KFold(n_splits=10, random_state=seed)
cart = DecisionTreeClassifier()

num_trees = 150

model = BaggingClassifier(base_estimator=cart, n_estimators=num_trees, random_state=seed)

results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())

0.7733766233766234

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import RandomForestClassifier

path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
array = data.values
X = array[:,0:8]
Y = array[:,8]

seed = 7
kfold = KFold(n_splits=10, random_state=seed)

num_trees = 150
max_features = 5

model = RandomForestClassifier(n_estimators=num_trees, max_features=max_features)

results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())

0.7629357484620642

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import ExtraTreesClassifier

path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
array = data.values
X = array[:,0:8]
Y = array[:,8]

seed = 7
kfold = KFold(n_splits=10, random_state=seed)

num_trees = 150
max_features = 5

model = ExtraTreesClassifier(n_estimators=num_trees, max_features=max_features)

results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())

0.7551435406698566

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import AdaBoostClassifier

path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
array = data.values
X = array[:,0:8]
Y = array[:,8]

seed = 5
kfold = KFold(n_splits=10, random_state=seed)

num_trees = 50

model = AdaBoostClassifier(n_estimators=num_trees, random_state=seed)

results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())

0.7539473684210527

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import GradientBoostingClassifier

path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
array = data.values
X = array[:,0:8]
Y = array[:,8]

seed = 5
kfold = KFold(n_splits=10, random_state=seed)

num_trees = 50

model = GradientBoostingClassifier(n_estimators=num_trees, random_state=seed)

results = cross_val_score(model, X, Y, cv=kfold)
print(results.mean())

0.7746582365003418

0.7382262474367738

import numpy
from pandas import read_csv
from sklearn.linear_model import Ridge
from sklearn.model_selection import GridSearchCV

path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
array = data.values
X = array[:,0:8]
Y = array[:,8]

alphas = numpy.array([1,0.1,0.01,0.001,0.0001,0])
param_grid = dict(alpha=alphas)

model = Ridge()
grid = GridSearchCV(estimator=model, param_grid=param_grid)
grid.fit(X, Y)

print(grid.best_score_)
print(grid.best_estimator_.alpha)

0.2796175593129722
1.0

import numpy
from pandas import read_csv
from scipy.stats import uniform
from sklearn.linear_model import Ridge
from sklearn.model_selection import RandomizedSearchCV

path = r"C:\pima-indians-diabetes.csv"
headernames = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(path, names=headernames)
array = data.values
X = array[:,0:8]
Y = array[:,8]

param_grid = {'alpha': uniform()}
model = Ridge()
random_search = RandomizedSearchCV(estimator=model, param_distributions=param_grid, n_iter=50,
random_state=7)
random_search.fit(X, Y)

print(random_search.best_score_)
print(random_search.best_estimator_.alpha)

0.27961712703051084
0.9779895119966027
0.9779895119966027