Four regression python assignment answer

Four regression python assignment answer

import pandas as pd

import numpy as np

from sklearn import preprocessing

import matplotlib.pyplot as plot

path = “C:/Users/Vic Og/Downloads/master.csv”

df = pd.read_csv(path)

df = df.dropna()

df = df.replace(r’^\s*$’, np.nan, regex=True)

df.isnull().sum()

X = df.iloc[:, 25].values.reshape(-1, 1) # independent variables

y = df.iloc[:, 25].values.reshape(-1, 1) # dependent variable

print(X.shape)

print(y.shape)

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=44)

from sklearn.tree import DecisionTreeRegressor

regrassor = DecisionTreeRegressor(random_state = 0)

regrassor.fit(X_test, y_test)

regPred = regrassor.predict(X_test)

print(“Decision Tree Regression predictions”)

print(regPred)

print(‘R squared training set’, round(regrassor.score(X, y)*100, 2))

print(‘R squared test set’, round(regrassor.score(X, y)*100, 2))

print(“”)

from sklearn.linear_model import Lasso

lasso = Lasso(alpha=1.0)

lasso.fit(X_train, y_train)

lassoPred = lasso.predict(X_test)

print(“Lasso Regression predictions”)

print(lassoPred)

print(‘R squared training set’, round(lasso.score(X, y)*100, 2))

print(‘R squared test set’, round(lasso.score(X, y)*100, 2))

print(“”)

from sklearn.linear_model import LinearRegression

linearReg =LinearRegression().fit(X_train, y_train)

print(“Linear Regression predictions”)

linPred = linearReg.predict(X_test)

print(linPred)

print(‘R squared training set’, round(linearReg.score(X_train, y_train)*100, 2))

print(‘R squared test set’, round(linearReg.score(X_train, y_train)*100, 2))

print(”)

# from sklearn.ensemble import RandomForestClassifier

# forest = RandomForestClassifier()

# forest.fit(X_train, y_train)

# print(“Random Forest Regression predictions”)

# forestPred = forest.predict(X_test)

# print(forestPred)

# print(‘R squared training set’, round(forest.score(X, y)*100, 2))

# print(‘R squared test set’, round(forest.score(X, y)*100, 2))

# print(“”)

plot.scatter(X_test, y_test, color = ‘red’)

plot.plot(X_train, y_train, color = ‘blue’)

plot.show()