jainanchit51

import pandas as pd
dataframe = pd.read_csv(‘breast-cancer-wisconsin.csv’, engine=’python’)
dataframe = dataframe.drop([‘bare_nucleoli’], axis=1)

jainanchit51

import seaborn as sns
import matplotlib.pyplot as plt
sns.set(style=’ticks’, color_codes=True)
plt.figure(figsize=(14, 12))
sns.heatmap(dataframe.astype(float).corr(), linewidths=0.1, square=True, linecolor=’white’, annot=True)
plt.show()

jainanchit51

fig = plt.figure()
ax = sns.countplot(x=’bland_chromatin’, hue=’class’, data=dataframe)
ax.set(xlabel=’Bland Chromatin’, ylabel=’No of cases’)
fig.suptitle(“Bland Chromatin w.r.t. Class”, y=0.96)

jainanchit51

#handling na
for label in ['clump_thickness','size_uniformity','shape_uniformity','marginal_adhesion']:
    dataframe[label] = dataframe[label].fillna(method='ffill')

jainanchit51

import pandas as pd
import numpy as np

# reading data
dataframe  = pd.read_csv('home.txt',names=["size","bedroom","price"])
 

# normalizing data

jainanchit51

   size  bedroom  price
0  2104        3  399900
1  1600        3  329900
2  2400        3  369000
3  1416        2  232000
4  3000        4  539900

jainanchit51

  size      bedroom   price
0  0.130010 -0.223675  0.475747
1 -0.504190 -0.223675 -0.084074
2  0.502476 -0.223675  0.228626
3 -0.735723 -1.537767 -0.867025
4  1.257476  1.090417  1.595389

jainanchit51

    def train(self,learning_rate,iter):
    

        alpha = learning_rate
        iterations = range(0,iter)
       
        # here x is columns

        X = self.x_input

jainanchit51

def cost_calculation(self,X,y,theta):
        inner = np.power(((X @ theta.T) - y), 2) # @ means matrix multiplication of arrays. If we want to use * for multiplication we will have to convert all arrays to matrices
        return np.sum(inner) / (2 * len(X))

jainanchit51

 def _gradient_descent(self,X, y, theta, alpha, iterations):
        for i in (iterations):
            theta = theta - (alpha/len(X)) * np.sum((X @ theta.T - y) * X, axis=0)
            cost = self.cost_calculation(X, y, theta)