linear_regression.py

import pandas as pd
import numpy as np
from sklearn import svm
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.metrics import confusion_matrix, accuracy_score, classification_report
from sklearn.model_selection import cross_val_score, train_test_split
from sklearn.metrics import accuracy_score, mean_squared_error, r2_score

dataset = pd.read_csv("dataset.csv")
print ("Total number of rows in dataset: {}\n".format(len(dataset)))
print(dataset.head())

features = ['Day','Month','Year','Humidity','Max Temperature','Min Temperature',
            'Rainfall','Sea Level Pressure','Sunshine','Wind Speed']
target = 'Cloud'

x_train, x_test, y_train, y_test = train_test_split(dataset[features], dataset[target],
                                                    train_size=0.7, test_size=0.3, shuffle=False)

# Print samples after running train_test_split
print("X_train: {}, Y_train: {}".format(len(x_train), len(x_test)))
print("X_train: {}, Y_train: {}".format(len(y_train), len(y_test)))

print("\n")

model = LinearRegression()
model.fit(x_train, y_train)

# Print results to evaluate model
print("Showing Performance Metrics for Naive Bayes Gaussian\n")

print ("Training Accuracy: {}".format(model.score(x_train, y_train)))
predicted = model.predict(x_test)
print ("Testing Accuracy: {}".format(accuracy_score(y_test, predicted)))