
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns


df=pd.read_csv('Customers EDA+stats.csv')


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 500 entries, 0 to 499
Data columns (total 16 columns):
 #   Column                         Non-Null Count  Dtype  
---  ------                         --------------  -----  
 0   order_id                       500 non-null    object 
 1   customer_id                    500 non-null    object 
 2   date                           500 non-null    object 
 3   nearest_warehouse              500 non-null    object 
 4   shopping_cart                  500 non-null    object 
 5   order_price                    500 non-null    int64  
 6   delivery_charges               500 non-null    float64
 7   customer_lat                   500 non-null    float64
 8   customer_long                  500 non-null    float64
 9   coupon_discount                500 non-null    int64  
 10  order_total                    500 non-null    float64
 11  season                         500 non-null    object 
 12  is_expedited_delivery          500 non-null    bool   
 13  distance_to_nearest_warehouse  500 non-null    float64
 14  latest_customer_review         499 non-null    object 
 15  is_happy_customer              500 non-null    bool   
dtypes: bool(2), float64(5), int64(2), object(7)
memory usage: 55.8+ KB


df.head()


df.describe()


df.isnull().sum()

order_id                         0
customer_id                      0
date                             0
nearest_warehouse                0
shopping_cart                    0
order_price                      0
delivery_charges                 0
customer_lat                     0
customer_long                    0
coupon_discount                  0
order_total                      0
season                           0
is_expedited_delivery            0
distance_to_nearest_warehouse    0
latest_customer_review           1
is_happy_customer                0
dtype: int64


df['latest_customer_review'] = df['latest_customer_review'].fillna('No feedBack')


df.isnull().sum()

order_id                         0
customer_id                      0
date                             0
nearest_warehouse                0
shopping_cart                    0
order_price                      0
delivery_charges                 0
customer_lat                     0
customer_long                    0
coupon_discount                  0
order_total                      0
season                           0
is_expedited_delivery            0
distance_to_nearest_warehouse    0
latest_customer_review           0
is_happy_customer                0
dtype: int64


df['nearest_warehouse'].unique()

array(['Thompson', 'Nickolson', 'Bakers', 'nickolson', 'thompson'],
      dtype=object)


df.nearest_warehouse=df.nearest_warehouse.str.title()


df['nearest_warehouse'].unique()

array(['Thompson', 'Nickolson', 'Bakers'], dtype=object)


df.duplicated().sum()

0


df['order_price'].plot(kind='hist',bins=20)
plt.title("Order Price distributed ")
plt.xlabel("Order Price ")
plt.ylabel("Frequency")
plt.show()


df['nearest_warehouse'].value_counts().plot(kind='bar', color=['r','b','g'])
plt.title("Quantity of the warehouses")
plt.xlabel("Warehouse")
plt.ylabel("Counts")

Text(0, 0.5, 'Counts')


plt.pie(df['is_happy_customer'].value_counts(), labels=['happy', 'Not happy'], autopct="%.1f%%")
plt.title("is_happy_customer or not")
plt.show()


df['date'] = pd.to_datetime(df['date'], errors='coerce')
df['month'] = df['date'].dt.month
sns.barplot(x='month', y='is_happy_customer', data=df, estimator=lambda x: len(x))
plt.suptitle('is_happy_customer(Across Months)')
plt.xlabel('Customer happiness')
plt.ylabel('Month')
plt.show()


sns.barplot(x='is_happy_customer', y='order_price', data=df, estimator=lambda x: x.mean())
plt.title("Avg Order Price by Customer happiness")
plt.xlabel("Customer happiness")
plt.ylabel("Avg Order Price")
plt.show()

	order_id	customer_id	date	nearest_warehouse	shopping_cart	order_price	delivery_charges	customer_lat	customer_long	coupon_discount	order_total	season	is_expedited_delivery	distance_to_nearest_warehouse	latest_customer_review	is_happy_customer
0	ORD182494	ID6197211592	2019-06-22	Thompson	[('Lucent 330S', 1), ('Thunder line', 2), ('iS...	12200	79.89	-37.815105	144.932843	10	11059.89	Winter	True	1.2800	perfect phone and trusted seller. phone itself...	True
1	ORD395518	ID0282825849	2019-12-29	Thompson	[('Thunder line', 1), ('Universe Note', 2)]	9080	62.71	-37.802736	144.951118	0	9142.71	Summer	False	1.1621	it keeps dropping calls the wifi don't work th...	False
2	ORD494479	ID0579391891	2019-03-02	Nickolson	[('Thunder line', 1), ('pearTV', 2)]	10670	65.87	-37.821302	144.957581	10	9668.87	Autumn	False	1.0949	five stars this is a great cheap phone.	True
3	ORD019224	ID4544561904	2019-01-12	Nickolson	[('Universe Note', 1), ('Alcon 10', 2), ('Oliv...	24800	57.61	-37.811416	144.973073	15	21137.61	Summer	False	0.8571	charger did not fit the charger didn't fit.	False
4	ORD104032	ID6231506320	2019-11-28	Nickolson	[('Universe Note', 1), ('Olivia x460', 1), ('i...	9145	75.54	37.823859	144.969892	25	6934.29	Spring	False	0.5867	four stars good	True

	order_price	delivery_charges	customer_lat	customer_long	coupon_discount	order_total	distance_to_nearest_warehouse
count	500.000000	500.000000	500.000000	500.000000	500.000000	5.000000e+02	500.000000
mean	25522.216000	76.658200	-35.835234	144.969494	10.890000	3.920967e+04	2.204224
std	86333.729169	14.481465	12.045393	0.022720	8.649134	2.741940e+05	8.812416
min	585.000000	46.350000	-37.827123	144.924967	0.000000	6.392900e+02	0.107800
25%	7050.000000	65.982500	-37.818222	144.953488	5.000000	6.454735e+03	0.751425
50%	12807.500000	76.310000	-37.812165	144.965357	10.000000	1.129396e+04	1.030100
75%	20360.000000	82.555000	-37.805364	144.983985	15.000000	1.811919e+04	1.408625
max	947691.000000	114.040000	37.826339	145.019837	25.000000	5.688270e+06	94.973400