Machine Learning 简明教程

# Importing the necessary libraries
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# Load the diabetes dataset
diabetes = pd.read_csv(r'C:\Users\Leekha\Desktop\diabetes.csv')

# Define the predictor variables (X) and the target variable (y)
X = diabetes.iloc[:, :-1].values
y = diabetes.iloc[:, -1].values

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)

# Create an empty set of features
selected_features = set()

# Set the maximum number of features to be selected
max_features = 8

# Iterate until the desired number of features is reached
while len(selected_features) < max_features:

   # Set the best feature and the best score to be 0
   best_feature = None
   best_score = 0

   # Iterate over all the remaining features
   for i in range(X_train.shape[1]):

      # Skip the feature if it's already selected
      if i in selected_features:
         continue

      # Select the current feature and fit a linear regression model
      X_train_selected = X_train[:, list(selected_features) + [i]]
      regressor = LinearRegression()
      regressor.fit(X_train_selected, y_train)

      # Compute the score on the testing set
      X_test_selected = X_test[:, list(selected_features) + [i]]
      score = regressor.score(X_test_selected, y_test)

      # Update the best feature and score if the current feature performs better
      if score > best_score:
         best_feature = i
         best_score = score

   # Add the best feature to the set of selected features
   selected_features.add(best_feature)

   # Print the selected features and the score
   print('Selected Features:', list(selected_features))
   print('Score:', best_score)