Python

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import statsmodels.api as sm
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score
import warnings
#from IPython import get_ipython
#ipy = get_ipython()
#if ipy is not None:
#    ipy.run_line_magic('matplotlib', 'inline')
sns.set()
#%matplotlib inline

df = pd.read_csv("./SalaryData1.csv")
print(df.shape)
print(df.isnull().values.any())

# -*- coding: utf-8 -*-
"""
Regression lineaire avec des listes en entrées
"""

import matplotlib.pyplot as plt
import numpy as np
import statsmodels.api as sm


#Farm size in hectares
X=[1,1,2,2,2.3,3,3,3.5,4,4.3]
#Crop yield in tons
Y=[6.9,6.7,13.8,14.7,16.5,18.7,17.4,22,29.4,34.5]
"""
#    By default, OLS implementation of statsmodels does not include an intercept 
#     in the model unless we are using formulas.
#    We need to explicitly specify the use of intercept in OLS method by 
#     adding a constant term.
X_1 = sm.add_constant(X)
#print(X_1)

# -*- coding: utf-8 -*-
"""
Created on Thu Dec 13 14:50:40 2018

@author: K
"""

import numpy as np
import time
import scipy.io
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split

datas = scipy.io.loadmat('ex4data1.mat')
X = datas["X"]
y =  datas["y"]
im = X[2098].reshape(20, 20);
plt.imshow(im, cmap='gray')
#plt.imshow(X[0]).reshape([20, 20]);


#print(type(X[0]))
#realout = 
Y = np.zeros((5000,1))
for i in range(0, 5000):
    for j in range(1, 10):
        if np.mod(y[i],2) == 0:
            Y[i,0] = 1
        else: