Project 2 - EDA on Vehicle Insurance Customer Data

# Step 1 : Reading data

import pandas

tabel1 = pandas.read_csv("customer_details.csv")

tabel2 = pandas.read_csv("customer_policy_details.csv")

print(tabel1.head())

print(tabel2.head())

# Step 2: Checking and Cleaning the data

# 2.1 Null values

# 2.1.1 Tabel1

tabel1_labels={'0':'customer_id','1':'gender','2':',age','3':'driving_licence_present',4',':'region_code','5':'previously_insured',

'6':'vehicle_age'7':'vehicle_damage'}

# 2.1.1.1 counting the null values of each column of tabel1

for i in range(table1.shape[1]):

print(f"number of cells of {tabel1_labels[str(i)]} with null values =

{table1[str1(i)].isnull().sum()}")

tabel1.info()

# 2.1.1.2 dropping rows with null customer_id of tabel1

tabel1.dropna(subset=['0'],inplace=true)

print(f"number of cells of {tabel1_labels[str(0)} with null values =

{table1[str(0)].isnull().sum()}")

# 2.1.1.3 replacing all null values for numeric column by mean of tabel1

for i in range(2,6):

tabel1[str1(i)].fillna(tabel1[str(i)].mean(),inplace=True

{tabel1[str(i)].isnull().sum()}")

# 2.1.1.4 replacing all null values for Catergorical value by mode of tabel1

for i in range(1,6,7):

tabel1[str(i)].fillna(tabel1[str(i)].mode()[0],inplace=True)

print(f"number of cells of {tabel1_labels[str(i)]} with null values =

{tabel1[str(i).isnull().sum()}")

# 2.1.2 Tabel2

tabel2_labels={'0':'customer_id',':'annual_premium_INR',

'2':'sales_channel_code','3':'vintage','4':'response'}

# 2.1.2.1 counting the null values of each column of table2

for i in range (table2.shape[1]):

print(f"number of cells of {tabels2_labels[str(i)]} with null values is

{tabel2[str(i)].isnull().sum()}")

tabel2.info()

# 2.1.2.2 dropping rows with null customer_id of table2

tabel2.dropna(subset=['0'],inplace=True)

print(f"number of cells of {tabel1_labels[str(0)]} with null values =

{tabel2[str(0)].isnull().sum()}")

# 2.1.2.3 replacing all null values for numeric columns by mean of table2

for i in range(1,5):

# 2.2 Outliers

# 2.2.1 Tabel1

tabel1_limits ={}

for i in range(2,6):

computations = tabel1[str(i).describe(percentiles=[.25,.75])

mean = computations.values[1]

Q1 = computations.values[4] #25%

Q3 = computations.values[6] #75%

IQR =Q3-Q1

II = Q1-1.5*IQR #lower limit

hI = Q3+1.5*IQR # higher limit

tabel1_limits[str(i)] = (II,hI)

tabel_limits

# 2.2.1.1 generating a summary of count of all the outliers column wise of tabel1

(only for numeric columns)

tabel1_outliers = {'2':0,'3':0,'4':0','5':0}

for j in tabel1.index:

for i in range(2,6):

if (tabel1_limits[str(i)][0]!=tabel1_limits[str(i)][1]) and(tabel1.loc[j,

str(i)]>tabel1_limits[str(i)][1] or tabel1.loc[j,str(i)]<tabel1_limits[str(i)][0]):

tabel1_outliers

# 2.1.2.2 replacing all outliers values for numeric columns by mean for tabel1

# though as can be seen above,there are no outliers at all!, anyways the code is following

for j in tabel1.index:

for i in range(2,6):

if tabel1.loc[j,str(i)]<tabel1_limits[str(i)][0]:

tabel1.loc[j,str(i)]=tabel1[str(i)].mean()

if tabel1.loc[j,str(i)]>tabel_limits[str(i)][1]:

table1.loc[j,str(i)]=tabel1[str(i)].mean()