Project 1

Data cleaning on Automobile 1985 dataset and perform descriptive analytics.

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns

from sklearn.preprocessing import StandardScaler

 

#Assign names to each column

column_name=['symboling','normalized_losses','make','fuel','aspiration','num_of_doors','body_style','drive_wheels','engine_location','wheel_base','length','width','height','curb_weight','engine_type','num_of_cylinders','engine_size','fuel_system','bore','stroke','compression_ratio','horsepower','peak_rpm','city_mpg','highway_mpg','price']

 

#Read dataset

df=pd.read_csv('auto.csv',names = column_name)

print(df.columns)

 

print(df.info())

print(df.shape)

print(df.head())

 

# Replacing ? with NAN

df.replace("?",np.nan,inplace=True)

print(df.head())

 

#Converting datatype

#pd.set_option('display.max_columns', None)

df['normalized_losses']=df['normalized_losses'].astype(float)

df['bore']=df['bore'].astype(float)

df['stroke']=df['stroke'].astype(float)

df['horsepower']=df['horsepower'].astype(float)

df['peak_rpm']=df['peak_rpm'].astype(float)

df['price']=df['price'].astype(float)

 

print(df.describe())

 

#Finding total null values

print(df.isna().sum())

 

#Dealing with null values

 

#Replacing with mean values

df['normalized_losses'].replace(np.nan, 122,inplace=True)

df['bore'].replace(np.nan, 3.329050,inplace=True)

df['stroke'].replace(np.nan, 3.258300,inplace=True)

df['horsepower'].replace(np.nan, 104.222772,inplace=True)

df['peak_rpm'].replace(np.nan, 5125.990099,inplace=True)

 

#Replacing with highest frequency values

print(df['num_of_doors'].value_counts())

df['num_of_doors'].replace(np.nan, 'four',inplace=True)

 

#Dropping values

df.dropna(subset=["price"], axis=0, inplace=True)

df.reset_index(drop=True, inplace=True)

print(df.head())

 

 

#Feature engineering

df['fuel']=pd.get_dummies(df['fuel'],drop_first=True)

 

df['aspiration']=pd.get_dummies(df['aspiration'],drop_first=True)

 

df['num_of_doors']=pd.get_dummies(df['num_of_doors'],drop_first=True)

 

df['engine_location']=pd.get_dummies(df['engine_location'],drop_first=True)

 

df['num_of_cylinders'].replace('two', 2,inplace=True)

df['num_of_cylinders'].replace('three', 3,inplace=True)

df['num_of_cylinders'].replace('four', 4,inplace=True)

df['num_of_cylinders'].replace('five', 5,inplace=True)

df['num_of_cylinders'].replace('six', 6,inplace=True)

df['num_of_cylinders'].replace('eight', 8,inplace=True)

df['num_of_cylinders'].replace('twelve', 12,inplace=True)

df['num_of_cylinders']=df['num_of_cylinders'].astype(int)

 

gd = pd.get_dummies(df['drive_wheels'], prefix='dw_',drop_first=True)

df = pd.merge(left=df,right=gd,left_index=True,right_index=True)

 

 

 

#Dropping unwanted features

df=df.drop(['make','drive_wheels','engine_type','fuel_system','body_style'],axis=1)

print(df.info())

 

 

#Corelation matrix

corr=df.corr().index

 

 

#Dropping highly corelated features

df=df.drop(['highway_mpg','compression_ratio'],axis=1)

print(df.info())

print(df.shape)

 

#Standardizing the data

sc=StandardScaler()

df=sc.fit_transform(df)

column_name2=['symboling','normalized_losses','fuel','aspiration','num_of_doors','engine_location','wheel_base','length','width','height','curb_weight','num_of_cylinders','engine_size','bore','stroke','horsepower','peak_rpm','city_mpg','price','dw__fwd','dw__rwd']

df=pd.DataFrame(df)

df.columns=column_name2

print(df.head())

plt.scatter(df['wheel_base'],df['price'])

plt.xlabel('wheel_base')

plt.ylabel('price')