Project 2 - EDA on Vehicle Insurance Customer Data

Added column names to both the data sets

calculated the null values of both the data sets column wise using .isnull() and .sum() function

Drop Null values for customer_id using .dropna() function.

Replaced all null values for numeric columns by mean using .fillna() function which is used to replace NaN values.

Replaced all null values for Categorical columns by mode using .fillna() function which is used to replace NaN values.

Generated a summary of count of all the outliers column wise. outliers are the values that fall more than three standard deviations from mean.

For getting percentile value, used pd.describe() function for both the data sets.

for this used the label based indexing i.e., loc().

No outliers in age column 
Annual premium is an outlier
No outliers in vintage column

Removed white spaces using strip()  function 

case correction using str.lower() function

Created  a Master table using merge() function()

calculated Gender wise average annual premium i.e, mean
calculated Age wise average annual premium

Data is balanced between the two genders.

There is no relationship between Person age and annual premium

​