10/6/24, 6:55 PM DMV_1 - Jupyter Notebook

In [1]: import pandas as pd

In [2]: csv_data = pd.read_csv('sales_data.csv', encoding='ISO-8859-1')

In [3]: excel_data = pd.read_excel('sales_data.xlsx')

In [4]: json_data = pd.read_json('sales_data.json')

In [5]: print(csv_data.info())
print(excel_data.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2823 entries, 0 to 2822
Data columns (total 25 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 ORDERNUMBER 2823 non-null int64
1 QUANTITYORDERED 2823 non-null int64
2 PRICEEACH 2823 non-null float64
3 ORDERLINENUMBER 2823 non-null int64
4 SALES 2823 non-null float64
5 ORDERDATE 2823 non-null object
6 STATUS 2823 non-null object
7 QTR_ID 2823 non-null int64
8 MONTH_ID 2823 non-null int64
9 YEAR_ID 2823 non-null int64
10 PRODUCTLINE 2823 non-null object
11 MSRP 2823 non-null int64
12 PRODUCTCODE 2823 non-null object
13 CUSTOMERNAME 2823 non-null object
14 PHONE 2823 non-null object
15 ADDRESSLINE1 2823 non-null object
16 ADDRESSLINE2 302 non-null object
17 CITY 2823 non-null object
18 STATE 1337 non-null object
19 POSTALCODE 2747 non-null object
20 COUNTRY 2823 non-null object
21 TERRITORY 1749 non-null object
22 CONTACTLASTNAME 2823 non-null object
23 CONTACTFIRSTNAME 2823 non-null object
24 DEALSIZE 2823 non-null object
dtypes: float64(2), int64(7), object(16)
memory usage: 551.5+ KB
None
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 390 entries, 0 to 389
Data columns (total 5 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Postcode 390 non-null int64
1 Sales_Rep_ID 390 non-null int64
2 Sales_Rep_Name 390 non-null object
3 Year 390 non-null int64
4 Value 390 non-null float64
dtypes: float64(1), int64(3), object(1)
memory usage: 15.4+ KB
None

In [6]: print(json_data.info())

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9999 entries, 0 to 9998
Data columns (total 7 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 id 9999 non-null int64
1 email 9999 non-null object
2 first 9999 non-null object
3 last 9999 non-null object
4 company 9999 non-null object
5 created_at 9999 non-null datetime64[ns, UTC]
6 country 9999 non-null object
dtypes: datetime64[ns, UTC](1), int64(1), object(5)
memory usage: 546.9+ KB
None

localhost:8888/notebooks/BE_PRACTICALS/DMV_1.ipynb 1/4
10/6/24, 6:55 PM DMV_1 - Jupyter Notebook

In [7]: csv_data.head()

Out[7]:
ORDERNUMBER QUANTITYORDERED PRICEEACH ORDERLINENUMBER SALES ORDERDATE STATUS QTR_ID MONTH_ID YEAR_ID ... ADDRESS

2/24/2003 897 Long

0 10107 30 95.70 2 2871.00 Shipped 1 2 2003 ...
0:00 A

59
1 10121 34 81.35 5 2765.90 5/7/2003 0:00 Shipped 2 5 2003 ...
l'A

27
2 10134 41 94.74 2 3884.34 7/1/2003 0:00 Shipped 3 7 2003 ... Colone

8/25/2003 78934
3 10145 45 83.26 6 3746.70 Shipped 3 8 2003 ...
0:00

10/10/2003
4 10159 49 100.00 14 5205.27 Shipped 4 10 2003 ... 7734 Str
0:00

5 rows × 25 columns

In [8]: csv_data.columns

Out[8]: Index(['ORDERNUMBER', 'QUANTITYORDERED', 'PRICEEACH', 'ORDERLINENUMBER',

'SALES', 'ORDERDATE', 'STATUS', 'QTR_ID', 'MONTH_ID', 'YEAR_ID',
'PRODUCTLINE', 'MSRP', 'PRODUCTCODE', 'CUSTOMERNAME', 'PHONE',
'ADDRESSLINE1', 'ADDRESSLINE2', 'CITY', 'STATE', 'POSTALCODE',
'COUNTRY', 'TERRITORY', 'CONTACTLASTNAME', 'CONTACTFIRSTNAME',
'DEALSIZE'],
dtype='object')

In [9]: excel_data.head()

Out[9]:
Postcode Sales_Rep_ID Sales_Rep_Name Year Value

0 2121 456 Jane 2011 84219.497311

1 2092 789 Ashish 2012 28322.192268

2 2128 456 Jane 2013 81878.997241

3 2073 123 John 2011 44491.142121

4 2134 789 Ashish 2012 71837.720959

In [15]: excel_data.columns

Out[15]: Index(['Postcode', 'Sales_Rep_ID', 'Sales_Rep_Name', 'Year', 'Value'], dtype='object')

In [10]: json_data.head()

Out[10]:
id email first last company created_at country

0 1 [email protected] Torrey Veum Hilll, Mayert and Wolf 2014-12-25 04:06:27.981000+00:00 Switzerland

1 2 [email protected] Micah Sanford Stokes-Reichel 2014-07-03 16:08:17.044000+00:00 Democratic People's Republic of Korea

2 3 [email protected] Hollis Swift Rodriguez, Cartwright and Kuhn 2014-08-18 06:15:16.731000+00:00 Tunisia

3 4 [email protected] Perry Leffler Sipes, Feeney and Hansen 2014-07-10 11:31:40.235000+00:00 Chad

4 5 [email protected] Janelle Hagenes Lesch and Daughters 2014-04-21 15:05:43.229000+00:00 Swaziland

In [14]: json_data.columns

Out[14]: Index(['id', 'email', 'first', 'last', 'company', 'created_at', 'country'], dtype='object')

In [23]: csv_data['COUNTRY'] = csv_data['COUNTRY'].astype(str)

excel_data['Postcode'] = excel_data['Postcode'].astype(str) # Assuming Postcode is analogous to Country
json_data['country'] = json_data['country'].astype(str)

In [44]: csv_selected = csv_data[['COUNTRY', 'ORDERNUMBER', 'SALES', 'YEAR_ID']].rename(columns={'COUNTRY': 'Country', 'YEAR_ID':'Yea

excel_selected = excel_data[['Postcode', 'Year', 'Value']].rename(columns={'Postcode': 'Country'})
json_selected = json_data[['country', 'email', 'first']].rename(columns={'country': 'Country'})

In [55]: combined_data = pd.merge(csv_selected, excel_selected, on=('Year','Country'), how='outer')

combined_data = pd.merge(combined_data, json_selected, on='Country', how='outer')

localhost:8888/notebooks/BE_PRACTICALS/DMV_1.ipynb 2/4
10/6/24, 6:55 PM DMV_1 - Jupyter Notebook

In [56]: combined_data.head()

Out[56]:
Country ORDERNUMBER SALES Year Value email first

0 USA 10107.0 2871.00 2003.0 NaN NaN NaN

1 USA 10145.0 3746.70 2003.0 NaN NaN NaN

2 USA 10159.0 5205.27 2003.0 NaN NaN NaN

3 USA 10168.0 3479.76 2003.0 NaN NaN NaN

4 USA 10201.0 2168.54 2003.0 NaN NaN NaN

In [57]: combined_data.tail()

Out[57]:
Country ORDERNUMBER SALES Year Value email first

82151 China NaN NaN NaN NaN [email protected] Christopher

82152 China NaN NaN NaN NaN [email protected] Hermann

82153 China NaN NaN NaN NaN [email protected] Leann

82154 China NaN NaN NaN NaN [email protected] Cierra

82155 China NaN NaN NaN NaN [email protected] Juliana

In [58]: combined_data.shape

Out[58]: (82156, 7)

In [59]: combined_data.isna().sum()

Out[59]: Country 0
ORDERNUMBER 9700
SALES 9700
Year 9310
Value 81766
email 1538
first 1538
dtype: int64

In [60]: combined_data.dtypes

Out[60]: Country object

ORDERNUMBER float64
SALES float64
Year float64
Value float64
email object
first object
dtype: object

In [64]: combined_data.describe()

Out[64]:
ORDERNUMBER SALES Year

count 72456.000000 72456.000000 72846.000000

mean 10262.038727 3535.301342 2003.891854

std 94.405512 1831.479392 0.926602

min 10100.000000 482.130000 2003.000000

25% 10180.000000 2184.000000 2003.000000

50% 10262.000000 3160.250000 2004.000000

75% 10347.000000 4496.800000 2004.000000

max 10425.000000 14082.800000 2013.000000

In [70]: combined_data['Year'] = combined_data['Year'].astype(int)

In [71]: mean_year = combined_data['Year'].mean() # Calculate the mean of the Year column

combined_data['Year'].fillna(mean_year, inplace=True)

In [72]: mean_sales = combined_data['SALES'].mean()

​
combined_data['SALES'].fillna(mean_sales, inplace=True)

localhost:8888/notebooks/BE_PRACTICALS/DMV_1.ipynb 3/4
10/6/24, 6:55 PM DMV_1 - Jupyter Notebook

In [73]: import matplotlib.pyplot as plt

import seaborn as sns
​
# Bar plot
plt.figure(figsize=(10, 6))
sns.barplot(x=combined_data['Year'], y=combined_data['SALES'])
plt.title('Total Sales by Year')
plt.xticks(rotation=45)
plt.show()

In [ ]: ​

localhost:8888/notebooks/BE_PRACTICALS/DMV_1.ipynb 4/4