32 lines
1.0 KiB
Python
32 lines
1.0 KiB
Python
|
# Regression Linéaire Multiple
|
||
|
|
|
||
|
|
# Importer les librairies
|
||
|
|
import numpy as np
|
||
|
|
import matplotlib.pyplot as plt
|
||
|
|
import pandas as pd
|
||
|
|
|
||
|
|
# Importer le dataset
|
||
|
|
dataset = pd.read_csv('50_Startups.csv')
|
||
|
|
X = dataset.iloc[:, :-1].values
|
||
|
|
y = dataset.iloc[:, -1].values
|
||
|
|
|
||
|
|
# Gérer les variables catégoriques
|
||
|
|
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
|
||
|
|
labelencoder_X = LabelEncoder()
|
||
|
|
X[:, 3] = labelencoder_X.fit_transform(X[:, 3])
|
||
|
|
onehotencoder = OneHotEncoder(categorical_features = [3])
|
||
|
|
X = onehotencoder.fit_transform(X).toarray()
|
||
|
|
X = X[:, 1:]
|
||
|
|
|
||
|
|
# Diviser le dataset entre le Training set et le Test set
|
||
|
|
from sklearn.model_selection import train_test_split
|
||
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
|
||
|
|
|
||
|
|
# Construction du modèle
|
||
|
|
from sklearn.linear_model import LinearRegression
|
||
|
|
regressor = LinearRegression()
|
||
|
|
regressor.fit(X_train, y_train)
|
||
|
|
|
||
|
|
# Faire de nouvelles prédictions
|
||
|
|
y_pred = regressor.predict(X_test)
|
||
|
|
regressor.predict(np.array([[1, 0, 130000, 140000, 300000]]))
|