DA 2

Machine Learning Lab

Name: Suprit Darshan Shrestha
Reg.no: 19BCE2584

Simple Linear Regression

Dataset:

Cancer dataset used in this experiment it is the refined dataset. Two columns are used AVG and
Diagnosis. Where, Diagnosis and AVG are related in which <=128 is 0 and >=128 is 1. In which 0
is B(benign) and 1 is M(Malignant).

Code:
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('Data2.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1].values
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)
y_pred = regressor.predict(X_test)
pd.DataFrame(data={'Actuals': y_test, 'Predictions': y_pred})
plt.scatter(X_train, y_train, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color = 'blue')
plt.title('AVG vs Diagnosis (Training set)')
plt.xlabel('AVG')
plt.ylabel('Diagnosis')
plt.show()
plt.scatter(X_test, y_test, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color = 'blue')
plt.title('AVG vs Diagnosis (Test set)')
plt.xlabel('AVG')
plt.ylabel('Diagnosis')
plt.show()
Output:
Polynomial Regression
Dataset:

Only the Diag column is added in this dataset from the previous dataset.

Code:
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('Data3.csv')
X = dataset.iloc[:, 1:-1].values
y = dataset.iloc[:, -1].values
dataset.head()
from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(X, y)
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)
from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree = 4)
X_poly = poly_reg.fit_transform(X)
lin_reg_2 = LinearRegression()
lin_reg_2.fit(X_poly, y)
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=None, normalize=False)
plt.scatter(X, y, color = 'red')
plt.plot(X, lin_reg.predict(X), color = 'blue')
plt.title('Cancer Dataset Linear Regression')
plt.xlabel('AVG')
plt.ylabel('Diagnosis')
plt.show()
plt.scatter(X, y, color = 'red')
plt.plot(X, lin_reg_2.predict(poly_reg.fit_transform(X)), color = 'blue')
plt.title('Cancer Dataset Polynomial Regression')
plt.xlabel('AVG')
plt.ylabel('Diagnosis')
plt.show()
X_grid = np.arange(min(X), max(X), 0.1)
X_grid = X_grid.reshape((len(X_grid), 1))
plt.scatter(X, y, color = 'red')
plt.plot(X_grid, lin_reg_2.predict(poly_reg.fit_transform(X_grid)), color = 'blue')
plt.title('Cancer Dataset Polynomial Regression)')
plt.xlabel('AVG')
plt.ylabel('Diagnosis')
plt.show()
lin_reg.predict([[6.5]])
lin_reg_2.predict(poly_reg.fit_transform([[6.5]]))
Output:
Multiple Regression
Dataset:

The data that was refined in the previous experiment is used here. From the dataset below.

Code:
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from sklearn import datasets, linear_model, metrics
dataset = pd.read_csv('Data4.csv',header=None)
X = dataset.iloc[:, 1:-1].values
y = dataset.iloc[:, -1].values
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4,random_state=1)
reg = linear_model.LinearRegression()
reg.fit(X_train, y_train)
print('Coefficients: ', reg.coef_)
print('Variance score: {}'.format(reg.score(X_test, y_test)))
plt.style.use('fivethirtyeight')
plt.scatter(reg.predict(X_train), reg.predict(X_train) - y_train,color= "green", s = 10, label =
'Train data')
plt.scatter(reg.predict(X_test), reg.predict(X_test) - y_test,color = "blue", s = 10, label = 'Test
data')
plt.hlines(y = 0, xmin = 0, xmax = 50, linewidth = 2)
plt.legend(loc = 'upper right')
plt.title("Residual errors")
plt.show()

Output: