import pandas as pd
import matplotlib.pyplot as plt
link = “https://raw.githubusercontent.com/swapnilsaurav/MachineLearning/master/4_Position_Salaries.csv”
df = pd.read_csv(link)
print(df.describe())
X = df.iloc[:,1:2].values
y = df.iloc[:,2].values

”’
# 1. Replace the missing values with mean value
from sklearn.impute import SimpleImputer
import numpy as np
imputer = SimpleImputer(missing_values=np.nan, strategy=’mean’)
imputer = imputer.fit(X[:,1:3])
X[:,1:3] = imputer.transform(X[:,1:3])
#print(X)
”’
”’
# 2. Handling categorical values
# encoding
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
lc = LabelEncoder()
X[:,3] = lc.fit_transform(X[:,3])

from sklearn.compose import ColumnTransformer
transform = ColumnTransformer([(‘one_hot_encoder’, OneHotEncoder(),[3])],remainder=’passthrough’)
X=transform.fit_transform(X)
X = X[:,1:] # dropped one column
print(X)

”’
”’
After doing Backward elemination method we realized that all the state columns
are not significantly impacting the analysis hence removing those 2 columns too.

X = X[:,2:] # after backward elemination
”’
”’
# EDA – Exploratory Data Analysis
plt.scatter(x=df[‘Level’],y=df[‘Salary’])
plt.show()
”’

# 3. splitting it into train and test test
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=100)
print(X_train)

from sklearn.linear_model import LinearRegression
from sklearn import metrics
”’
# 4. Scaling / Normalization
from sklearn.preprocessing import StandardScaler
scale = StandardScaler()
X_train = scale.fit_transform(X_train[:,3:])
X_test = scale.fit_transform(X_test[:,3:])
print(X_train)
”’
”’
#Since dataset is too small, lets take entire data for training
X_train, y_train = X,y
X_test, y_test = X,y
”’
”’
## RUN THE MODEL

regressor = LinearRegression()
# fit – train the model
regressor.fit(X_train, y_train)
print(f”M/Coefficient/Slope = {regressor.coef_} and the Constant = {regressor.intercept_}”)

# y =
y_pred = regressor.predict(X_test)
result_df =pd.DataFrame({‘Actual’: y_test, ‘Predicted’: y_pred})
print(result_df)

# Analyze the output

mse = metrics.mean_squared_error(y_true=y_test, y_pred=y_pred)
print(“Root Mean Squared Error (Variance) = “,mse**0.5)
mae = metrics.mean_absolute_error(y_true=y_test, y_pred=y_pred)
print(“Mean Absolute Error = “,mae)
print(“R Square is (Variance)”,metrics.r2_score(y_test, y_pred))

## Bias is based on training data
y_pred_tr = regressor.predict(X_train)
mse = metrics.mean_squared_error(y_true=y_train, y_pred=y_pred_tr)
print(“Root Mean Squared Error (Bias) = “,mse**0.5)
print(“R Square is (Bias)”,metrics.r2_score(y_train, y_pred_tr))

# Plotting the data for output
plt.scatter(x=df[‘Level’],y=df[‘Salary’])
plt.plot(X,y_pred)
plt.xlabel(“Level”)
plt.ylabel(“Salary”)
plt.show()
”’

# 3. Model – Polynomial regression analysis
# y = C + m1 * X + m2 * x square
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import Pipeline

for i in range(1,10):
#prepare the parameters
parameters = [(‘polynomial’, PolynomialFeatures(degree=i)),(‘modal’,LinearRegression())]
pipe = Pipeline(parameters)
pipe.fit(X_train,y_train)
y_pred = pipe.predict(X)
## Bias is based on training data
y_pred_tr = pipe.predict(X_train)
mse = metrics.mean_squared_error(y_true=y_train, y_pred=y_pred_tr)
rmse_tr = mse ** 0.5
print(“Root Mean Squared Error (Bias) = “,rmse_tr)
print(“R Square is (Bias)”,metrics.r2_score(y_train, y_pred_tr))

## Variance is based on validation data
y_pred_tt = pipe.predict(X_test)
mse = metrics.mean_squared_error(y_true=y_test, y_pred=y_pred_tt)
rmse_tt = mse ** 0.5
print(“Root Mean Squared Error (Variance) = “, rmse_tt)
print(“R Square is (Variance)”, metrics.r2_score(y_test, y_pred_tt))
print(“Difference Between variance and bias = “,rmse_tt – rmse_tr)
# Plotting the data for output
plt.scatter(x=df[‘Level’],y=df[‘Salary’])
plt.plot(X,y_pred)
plt.title(“Polynomial Analysis degree =”+str(i))
plt.xlabel(“Level”)
plt.ylabel(“Salary”)
plt.show()