import numpy as np

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

pen_spark Generate a slider using jupyter widgets search Close

df = pd.read_csv('/DiwaliSalesData.csv', encoding='unicode_escape')
df.head()
df.tail()

Age
User_ID Cust_name Product_ID Gender Age Marital_Status State Zone Occupation Product_Category Orders Amount S
Group

11246 1000695 Manning P00296942 M 18-25 19 1 Maharashtra Western Chemical Office 4 370.0

11247 1004089 Reichenbach P00171342 M 26-35 33 0 Haryana Northern Healthcare Veterinary 3 367.0

Madhya
11248 1001209 Oshin P00201342 F 36-45 40 0 Central Textile Office 4 213.0
Pradesh

11249 1004023 Noonan P00059442 M 36-45 37 0 Karnataka Southern Agriculture Office 3 206.0

11250 1002744 Brumley P00281742 F 18-25 19 0 Maharashtra Western Healthcare Office 3 188.0

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 11251 entries, 0 to 11250
Data columns (total 15 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 User_ID 11251 non-null int64
1 Cust_name 11251 non-null object
2 Product_ID 11251 non-null object
3 Gender 11251 non-null object
4 Age Group 11251 non-null object
5 Age 11251 non-null int64
6 Marital_Status 11251 non-null int64
7 State 11251 non-null object
8 Zone 11251 non-null object
9 Occupation 11251 non-null object
10 Product_Category 11251 non-null object
11 Orders 11251 non-null int64
12 Amount 11239 non-null float64
13 Status 0 non-null float64
14 unnamed1 0 non-null float64
dtypes: float64(3), int64(4), object(8)
memory usage: 1.3+ MB
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 11251 entries, 0 to 11250
Data columns (total 15 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 User_ID 11251 non-null int64
1 Cust_name 11251 non-null object
2 Product_ID 11251 non-null object
3 Gender 11251 non-null object
4 Age Group 11251 non-null object
5 Age 11251 non-null int64
6 Marital_Status 11251 non-null int64
7 State 11251 non-null object
8 Zone 11251 non-null object
9 Occupation 11251 non-null object
10 Product_Category 11251 non-null object
11 Orders 11251 non-null int64
12 Amount 11239 non-null float64
13 Status 0 non-null float64
14 unnamed1 0 non-null float64
dtypes: float64(3), int64(4), object(8)
memory usage: 1.3+ MB

df.isnull()
 Age
User_ID Cust_name Product_ID Gender Age Marital_Status State Zone Occupation Product_Category Orders Amount Status
Group

0 False False False False False False False False False False False False False True

1 False False False False False False False False False False False False False True

2 False False False False False False False False False False False False False True

3 False False False False False False False False False False False False False True

4 False False False False False False False False False False False False False True

... ... ... ... ... ... ... ... ... ... ... ... ... ... ...

11246 False False False False False False False False False False False False False True

11247 False False False False False False False False False False False False False True

11248 False False False False False False False False False False False False False True

11249 False False False False False False False False False False False False False True

11250 False False False False False False False False False False False False False True

df.drop(['Status', 'unnamed1'], axis=1)

Age
User_ID Cust_name Product_ID Gender Age Marital_Status State Zone Occupation Product_Category Orders Amount
Group

0 1002903 Sanskriti P00125942 F 26-35 28 0 Maharashtra Western Healthcare Auto 1 23952.

1 1000732 Kartik P00110942 F 26-35 35 1 Andhra Pradesh Southern Govt Auto 3 23934.

2 1001990 Bindu P00118542 F 26-35 35 1 Uttar Pradesh Central Automobile Auto 3 23924.

3 1001425 Sudevi P00237842 M 0-17 16 0 Karnataka Southern Construction Auto 2 23912.

Food
4 1000588 Joni P00057942 M 26-35 28 1 Gujarat Western Auto 2 23877.
Processing

... ... ... ... ... ... ... ... ... ... ... ... ... .

11246 1000695 Manning P00296942 M 18-25 19 1 Maharashtra Western Chemical Office 4 370.

11247 1004089 Reichenbach P00171342 M 26-35 33 0 Haryana Northern Healthcare Veterinary 3 367.

Madhya
11248 1001209 Oshin P00201342 F 36-45 40 0 Central Textile Office 4 213.
Pradesh

11249 1004023 Noonan P00059442 M 36-45 37 0 Karnataka Southern Agriculture Office 3 206.

df["Amount"].median()

8109.0

df.isna()

Age
User_ID Cust_name Product_ID Gender Age Marital_Status State Zone Occupation Product_Category Orders Amount Status
Group

0 False False False False False False False False False False False False False True

1 False False False False False False False False False False False False False True

2 False False False False False False False False False False False False False True

3 False False False False False False False False False False False False False True

4 False False False False False False False False False False False False False True

... ... ... ... ... ... ... ... ... ... ... ... ... ... ...

11246 False False False False False False False False False False False False False True

11247 False False False False False False False False False False False False False True

11248 False False False False False False False False False False False False False True

11249 False False False False False False False False False False False False False True

11250 False False False False False False False False False False False False False True

df.isna().sum()
 0

User_ID 0

Cust_name 0

Product_ID 0

Gender 0

Age Group 0

Age 0

Marital_Status 0

State 0

Zone 0

Occupation 0

Product_Category 0

Orders 0

Amount 12

Status 11251

unnamed1 11251

dtype: int64

df.duplicated()

0 False

1 False

2 False

3 False

4 False

... ...

11246 False

11247 False

11248 False

11249 False

11250 False

11251 rows × 1 columns

dtype: bool

df.duplicated().sum()

df.drop_duplicates()

Age
User_ID Cust_name Product_ID Gender Age Marital_Status State Zone Occupation Product_Category Orders Amount
Group

0 1002903 Sanskriti P00125942 F 26-35 28 0 Maharashtra Western Healthcare Auto 1 23952.

1 1000732 Kartik P00110942 F 26-35 35 1 Andhra Pradesh Southern Govt Auto 3 23934.

2 1001990 Bindu P00118542 F 26-35 35 1 Uttar Pradesh Central Automobile Auto 3 23924.

3 1001425 Sudevi P00237842 M 0-17 16 0 Karnataka Southern Construction Auto 2 23912.

Food
4 1000588 Joni P00057942 M 26-35 28 1 Gujarat Western Auto 2 23877.
Processing

... ... ... ... ... ... ... ... ... ... ... ... ... .

11246 1000695 Manning P00296942 M 18-25 19 1 Maharashtra Western Chemical Office 4 370.

11247 1004089 Reichenbach P00171342 M 26-35 33 0 Haryana Northern Healthcare Veterinary 3 367.

Madhya
11248 1001209 Oshin P00201342 F 36-45 40 0 Central Textile Office 4 213.
Pradesh

11249 1004023 Noonan P00059442 M 36-45 37 0 Karnataka Southern Agriculture Office 3 206.

11250 1002744 Brumley P00281742 F 18-25 19 0 Maharashtra Western Healthcare Office 3 188.

11243 rows × 15 columns

0 False

1 False

2 False

3 False

4 False

... ...

11246 False

11247 False

11248 False

11249 False

11250 False

11251 rows × 1 columns

df.describe()

User_ID Age Marital_Status Orders Amount Status unnamed1

count 1.125100e+04 11251.000000 11251.000000 11251.000000 11239.000000 0.0 0.0

mean 1.003004e+06 35.421207 0.420318 2.489290 9453.610858 NaN NaN

std 1.716125e+03 12.754122 0.493632 1.115047 5222.355869 NaN NaN

min 1.000001e+06 12.000000 0.000000 1.000000 188.000000 NaN NaN

25% 1.001492e+06 27.000000 0.000000 1.500000 5443.000000 NaN NaN

50% 1.003065e+06 33.000000 0.000000 2.000000 8109.000000 NaN NaN

75% 1.004430e+06 43.000000 1.000000 3.000000 12675.000000 NaN NaN

1 006040 06 92 000000 1 000000 4 000000 23952 000000 N N N N

df.drop(['Status', 'unnamed1'], axis=1, inplace=True)

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 11251 entries, 0 to 11250
Data columns (total 13 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 User_ID 11251 non-null int64
1 Cust_name 11251 non-null object
2 Product_ID 11251 non-null object
3 Gender 11251 non-null object
4 Age Group 11251 non-null object
5 Age 11251 non-null int64
6 Marital_Status 11251 non-null int64
7 State 11251 non-null object
8 Zone 11251 non-null object
9 Occupation 11251 non-null object
10 Product_Category 11251 non-null object
11 Orders 11251 non-null int64
12 Amount 11239 non-null float64
dtypes: float64(1), int64(4), object(8)
memory usage: 1.1+ MB

df.describe()
 User_ID Age Marital_Status Orders Amount

count 1.125100e+04 11251.000000 11251.000000 11251.000000 11239.000000

mean 1.003004e+06 35.421207 0.420318 2.489290 9453.610858

std 1.716125e+03 12.754122 0.493632 1.115047 5222.355869

min 1.000001e+06 12.000000 0.000000 1.000000 188.000000

25% 1.001492e+06 27.000000 0.000000 1.500000 5443.000000

50% 1.003065e+06 33.000000 0.000000 2.000000 8109.000000

75% 1.004430e+06 43.000000 1.000000 3.000000 12675.000000

max 1.006040e+06 92.000000 1.000000 4.000000 23952.000000

Distributions

2-d distributions

Values

plt.figure(figsize=(4,4))
sns.barplot(x=df['Gender'],y=df['Amount'],data=df, estimator=sum)
plt.show()

plt.figure(figsize=(4,4))
sns.barplot(x='Marital_Status',y='Amount',data=df)
plt.show()
plt.figure(figsize=(10,10))
sns.lineplot(x='State',y='Amount',data=df)
plt.show()

add Code add Text