Regression for multiline

Multiline.py

#FOR MULTILINES
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sasbornInstance
from sklearn.model_selection

import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn import metrixcs
%matplotlib inline

dataset = pd.read_csv()

dataset.shape
dataset.describe
#clean null values
dataset.isnull().any()

dataset = dataset.fillna(method='ffill')

#divid the data
X= dataset[[]].values
y= dataset[].values

#Check average values of the column
plt.figure(figsize=(15,10))
plt.tight_layout()
seabornInstance.distplot(dataset['qualitly'])

#spilt the data 80/20 for train/test
X_train,X_test, y_train, y_test = train_test_spilt(X,y, test_size=0.2, random_state=0)

#WE A TRAIN DEM
regressor = LinearRegression()
regressor.fit(X_train,, y_train)

#for multi-line looking for the most effecient CoEf
coeff_df = pd.DataFrame(regressor.coef_,X.columns,columns=['Coefficent'])
coeff_df


#guessing games
y_pred = regressor.predict(X_test)


#check the difference between actual value and predicited value
df = pd.DataFrame({'Actual': y_test, 'Predicted': y_pred})
df1 = df.head(25)

#plot this
df1.plot(kind='bar' ,figsize=(10,8))
plt.grid(which='major', linestyle='-', linewidth='0.5',color='green')
plt.grid(which='minor'),linestyle='-', linewidth='0.5',color='black')
plt.show()

'''
#evaluate the performance of the algo
print('Mean Absolute Error:', 0.0)
print('Mean squared error':, 0.0)
print('Root Mean Sqaured Error': 0.0)
'''

#Done?