# Import libraries from sklearn.linear_model import LinearRegression # define data, create model and fit data X = Variables Y = Features Model = LinearRegression().fit(X, Y) # Score model Model.score(X, y) # Predict new values NewY = Model.Predict(NewX)
Created on Sun Oct 29 01:16:32 2017
@author: amisha
"""
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
#import data set
dataset = pd.read_csv('/home/amisha/Desktop/doc.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 1].values
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X, y)
from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree=2)
X_poly = poly_reg.fit_transform(X)
poly_reg.fit(X_poly, y)
lin_reg_2 = LinearRegression()
lin_reg_2.fit(X_poly, y)
plt.scatter(X, y, color='red')
plt.plot(X, LinearRegression.Predict(X), color='blue')
plt.title('age vs mortality (Polynomial Regression)')
plt.xlabel('age')
plt.ylabel('mortality')
plt.show()
y = dataset.iloc[:, 4].values
# Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder = LabelEncoder()
X[:, 3] = labelencoder.fit_transform(X[:, 3])
onehotencoder = OneHotEncoder(categorical_features=[3])
X = onehotencoder.fit_transform(X).toarray()
#Fitting Multiple Linear Regression to the training set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train)
#Predicting the Test set result
y_pred = regressor.Predict(X_test)
# 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)
#Optimal model with backpropagation
import statsmodel.formula.api as sm
#ajouter bO
X = np.append(arr=np.ones((50, 1)).astype(int), values=X, axis=1)
