import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns from sklearn.model_selection import train_test_split from sklearn.linear_model import LinearRegression from sklearn import metrics %matplotlib inline

df = pd.read_csv('Summary of Weather.csv')

df.shape

df.isnull().sum()

df_clean1 = df.dropna()

df_clean1.isnull().sum()

df_clean1.describe()

df.isnull().sum()

df.plot(x='MinTemp', y='MaxTemp', style='o') plt.title('MinTemp vs MaxTemp') plt.xlabel('Minimum Temperature') plt.ylabel('Maximum Temperature') plt.show()

plt.figure(figsize=(10,5)) plt.tight_layout() sns.distplot(df['MaxTemp'])

X = df['MinTemp'].values.reshape(-1,1) y = df['MaxTemp'].values.reshape(-1,1)

X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.2, random_state=0)

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

#intercept and slope respectively print(regressor.intercept_) print(regressor.coef_)

y_pred = regressor.predict(X_test)

df2= pd.DataFrame({'Actual': y_test.flatten(), 'Predicted': y_pred.flatten()}) df2.head(30)

df_plot = df2.head(20) df_plot.plot(kind='bar', figsize=(10,5)) plt.grid(which='major', linestyle='-', linewidth='0.5', color='green') plt.grid(which='minor', linestyle='-', linewidth='0.5', color='black') plt.show()

#new_data= pd.df'MinTemp', 'MaxTemp'}) data = [df['MinTemp'],df['MaxTemp']] headers = ['MinTemp','MaxTemp'] new_data = pd.concat(data,axis=1,keys=headers) print(new_data)

new_data.isnull().sum()

new_data.describe()

file_name = 'MinMax_Temperature.xlsx' new_data.to_excel(file_name)

pip install tabpy

python --version