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
| # Simple Linear Regression
# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
# Importing the dataset
dataset = pd.read_csv('Data_Small.csv', header = None)
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 7].values
# Encoding categorical data
# Encoding the Independent Variable
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X_3 = LabelEncoder()
X[:, 3] = labelencoder_X_3.fit_transform(X[:, 3])
labelencoder_X_4 = LabelEncoder()
X[:, 4] = labelencoder_X_4.fit_transform(X[:, 4])
labelencoder_X_5 = LabelEncoder()
X[:, 5] = labelencoder_X_5.fit_transform(X[:, 5])
labelencoder_X_6 = LabelEncoder()
X[:, 6] = labelencoder_X_6.fit_transform(X[:, 6])
onehotencoder = OneHotEncoder(categorical_features = [3,4,5,6])
X = onehotencoder.fit_transform(X).toarray()
# 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)
# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
# Fitting Logistic Regression to the Training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state = 0)
classifier.fit(X_train, y_train)
# Predicting the Test set results
y_pred = classifier.predict(X_test) |
Partager