Linear Regression (Service Level) 1

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split

from sklearn import metrics

#%matplotlib inline

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as seabornInstance

from numpy import array

ServiceLevel = pd.read_csv("Service Level.csv")

#print(ServiceLevel.head())

#print(ServiceLevel.shape)

#print(ServiceLevel.describe())

# Graph for Call Volumes vs Answered

ServiceLevel.plot(x='Volume Offered', y = 'SL', style='o')

plt.title('SL vs Volume Offered')

plt.xlabel('Volume Offered')

plt.ylabel('SL')

#plt.show()

# Average SL

plt.figure(figsize=(15,10))

plt.tight_layout()

seabornInstance.distplot(ServiceLevel['SL'])

#plt.show()

y = ServiceLevel['SL'].values.reshape(-1, 1)  # Create arrays for the feature / target variable

#print(y)

X = ServiceLevel['Volume Offered'].values.reshape(-1,1) # Create arrays for the response variables

#print(X)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state=42) # Split into training and test set

regressor = LinearRegression()

regressor.fit(X_train, y_train) # training the algorithm

print(regressor.intercept_) # retrieve the intercept

print(regressor.coef_) # retrieve the slop

#Result

#intercept: 0.50865504

#coefficient: 0.0002021

# For every 1 unit change in volume, the change in SL is about 0.0002021%

y_pred = regressor.predict(X_test)

#print(y_pred)

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

print(df)

df1 = df

df1.plot(kind='bar',figsize=(16,10))

plt.grid(which='major', linestyle='-', linewidth='0.5', color='green')

plt.grid(which='minor', linestyle=':', linewidth='0.5', color='black')

#plt.show()#

plt.scatter(X_test, y_test,  color='gray')

plt.plot(X_test, y_pred, color='red', linewidth=2)

#plt.show()

print('Mean Absolute Error:', metrics.mean_absolute_error(y_test, y_pred))

print('Mean Squared Error:', metrics.mean_squared_error(y_test, y_pred))

print('Root Mean Squared Error:', np.sqrt(metrics.mean_squared_error(y_test, y_pred)))

# Mean Absolute Error: 0.14387132265451136

# Mean Squared Error: 0.03385032038495754

# Root Mean Squared Error: 0.18398456561613408