Regression-Models-Python/Multiple-Linear.py at main · thanderoy/Regression-Models-Python · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
# Importing libraries
# -------------------
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
# ---------------------
dataset = pd.read_csv('add the dataset path here...')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 4].values

# Encoding categorical data
# -------------------------
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()

# Avoiding the Dummy Variable Trap
X = X[:, 1:]

# Splitting the dataset into the Training set and Test set
# --------------------------------------------------------
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)

# Fitting Multiple Linear Regression to the Training set
from sklearn.linear_model import LinearRegression
# Missing line-----------------------------------------
# Missing line-----------------------------------------


# Predicting the Test set results
# Missing line-----------------------------------------

# Building the optimal model using Backward Elimination
import statsmodels.formula.api as sm
X = np.append(arr=np.ones((50, 1)).astype(int), values=X, axis=1)
X_opt = X[:, [0, 1, 2, 3, 4, 5]]
regressor_OLS = sm.OLS(endog=y, exog=X_opt).fit()
regressor_OLS.summary()
X_opt = X[:, [0, 1, 3, 4, 5]]
regressor_OLS = sm.OLS(endog=y, exog=X_opt).fit()
regressor_OLS.summary()
X_opt = X[:, [0, 3, 4, 5]]
regressor_OLS = sm.OLS(endog=y, exog=X_opt).fit()
regressor_OLS.summary()
X_opt = X[:, [0, 3, 5]]
regressor_OLS = sm.OLS(endog=y, exog=X_opt).fit()
regressor_OLS.summary()
X_opt = X[:, [0, 3]]
regressor_OLS = sm.OLS(endog=y, exog=X_opt).fit()
regressor_OLS.summary()