sales-analysis

May 3, 2025

0.0.1 Import Necessary Libraries

[1]: import pandas as pd

import os
import matplotlib.pyplot as plt

0.0.2 Merge 12 Month of Sales Data into a Single CSV File

[2]: files = [file for file in os.listdir("./Sales_Data")]

for f in files:
print(f)

Sales_April_2019.csv
Sales_August_2019.csv
Sales_December_2019.csv
Sales_February_2019.csv
Sales_January_2019.csv
Sales_July_2019.csv
Sales_June_2019.csv
Sales_March_2019.csv
Sales_May_2019.csv
Sales_November_2019.csv
Sales_October_2019.csv
Sales_September_2019.csv

[3]: df_list = []

for dir in files:

file_path = os.path.join("./Sales_Data", dir) # use to combine multiple␣
↪parts of a file path

df = pd.read_csv(file_path)
df_list.append(df)

# concate all dataframes

combined_df = pd.concat(df_list, ignore_index=True)

# save all files in one file

combined_df.to_csv("all_data.csv", index=False)

1
[4]: all_data = pd.read_csv("all_data.csv")
all_data.head()

[4]: Order ID Product Quantity Ordered Price Each \

0 176558 USB-C Charging Cable 2 11.95
1 NaN NaN NaN NaN
2 176559 Bose SoundSport Headphones 1 99.99
3 176560 Google Phone 1 600
4 176560 Wired Headphones 1 11.99

Order Date Purchase Address

0 04/19/19 08:46 917 1st St, Dallas, TX 75001
1 NaN NaN
2 04/07/19 22:30 682 Chestnut St, Boston, MA 02215
3 04/12/19 14:38 669 Spruce St, Los Angeles, CA 90001
4 04/12/19 14:38 669 Spruce St, Los Angeles, CA 90001

0.0.3 Clean up the Data

[5]: all_data.isnull().sum()

[5]: Order ID 545

Product 545
Quantity Ordered 545
Price Each 545
Order Date 545
Purchase Address 545
dtype: int64

[6]: all_data = all_data.dropna(how="all")

[7]: all_data.isnull().sum()

[7]: Order ID 0
Product 0
Quantity Ordered 0
Price Each 0
Order Date 0
Purchase Address 0
dtype: int64

Find “OR” and dlt it

[8]: all_data.columns

[8]: Index(['Order ID', 'Product', 'Quantity Ordered', 'Price Each', 'Order Date',
'Purchase Address'],

2
 dtype='object')

[9]: all_data = all_data[all_data["Order Date"].str[0:2] != "Or"]

Convert Column to the Correct Type

[10]: all_data["Quantity Ordered"] = pd.to_numeric(all_data["Quantity Ordered"]) #␣
↪make int

all_data["Price Each"] = pd.to_numeric(all_data["Price Each"]) #␣

↪make float

Add Month Column

[11]: all_data["Month"] = all_data["Order Date"].str[0:2]
all_data["Month"] = all_data["Month"].astype("int32")
all_data.head()

[11]: Order ID Product Quantity Ordered Price Each \

0 176558 USB-C Charging Cable 2 11.95
2 176559 Bose SoundSport Headphones 1 99.99
3 176560 Google Phone 1 600.00
4 176560 Wired Headphones 1 11.99
5 176561 Wired Headphones 1 11.99

Order Date Purchase Address Month

0 04/19/19 08:46 917 1st St, Dallas, TX 75001 4
2 04/07/19 22:30 682 Chestnut St, Boston, MA 02215 4
3 04/12/19 14:38 669 Spruce St, Los Angeles, CA 90001 4
4 04/12/19 14:38 669 Spruce St, Los Angeles, CA 90001 4
5 04/30/19 09:27 333 8th St, Los Angeles, CA 90001 4

Add Sales Column

[12]: all_data["Sales"] = all_data["Quantity Ordered"] * all_data["Price Each"]
all_data

[12]: Order ID Product Quantity Ordered Price Each \

0 176558 USB-C Charging Cable 2 11.95
2 176559 Bose SoundSport Headphones 1 99.99
3 176560 Google Phone 1 600.00
4 176560 Wired Headphones 1 11.99
5 176561 Wired Headphones 1 11.99
… … … … …
186845 259353 AAA Batteries (4-pack) 3 2.99
186846 259354 iPhone 1 700.00
186847 259355 iPhone 1 700.00
186848 259356 34in Ultrawide Monitor 1 379.99
186849 259357 USB-C Charging Cable 1 11.95

3
 Order Date Purchase Address Month Sales
0 04/19/19 08:46 917 1st St, Dallas, TX 75001 4 23.90
2 04/07/19 22:30 682 Chestnut St, Boston, MA 02215 4 99.99
3 04/12/19 14:38 669 Spruce St, Los Angeles, CA 90001 4 600.00
4 04/12/19 14:38 669 Spruce St, Los Angeles, CA 90001 4 11.99
5 04/30/19 09:27 333 8th St, Los Angeles, CA 90001 4 11.99
… … … … …
186845 09/17/19 20:56 840 Highland St, Los Angeles, CA 90001 9 8.97
186846 09/01/19 16:00 216 Dogwood St, San Francisco, CA 94016 9 700.00
186847 09/23/19 07:39 220 12th St, San Francisco, CA 94016 9 700.00
186848 09/19/19 17:30 511 Forest St, San Francisco, CA 94016 9 379.99
186849 09/30/19 00:18 250 Meadow St, San Francisco, CA 94016 9 11.95

[185950 rows x 8 columns]

0.0.4 Which is the Best Month for Sales?

[13]: results = all_data.groupby("Month").sum()

[14]: plt.figure(figsize=(6,4))
months = range(1,13)
plt.bar(months, results["Sales"])
plt.xticks(months)
plt.xlabel("Month Number")
plt.ylabel("Sales in USD ($)")
plt.show()

4
 Add City Column
[15]: def get_city(address):
return address.split(",")[1]

def get_state(address):
return address.split(",")[2].split(" ")[1]

all_data["City"] = all_data["Purchase Address"].apply(lambda x: f"{get_city(x)}␣

↪({get_state(x)})")

all_data

[15]: Order ID Product Quantity Ordered Price Each \

0 176558 USB-C Charging Cable 2 11.95
2 176559 Bose SoundSport Headphones 1 99.99
3 176560 Google Phone 1 600.00
4 176560 Wired Headphones 1 11.99
5 176561 Wired Headphones 1 11.99
… … … … …
186845 259353 AAA Batteries (4-pack) 3 2.99
186846 259354 iPhone 1 700.00
186847 259355 iPhone 1 700.00
186848 259356 34in Ultrawide Monitor 1 379.99
186849 259357 USB-C Charging Cable 1 11.95

5
 Order Date Purchase Address Month \
0 04/19/19 08:46 917 1st St, Dallas, TX 75001 4
2 04/07/19 22:30 682 Chestnut St, Boston, MA 02215 4
3 04/12/19 14:38 669 Spruce St, Los Angeles, CA 90001 4
4 04/12/19 14:38 669 Spruce St, Los Angeles, CA 90001 4
5 04/30/19 09:27 333 8th St, Los Angeles, CA 90001 4
… … … …
186845 09/17/19 20:56 840 Highland St, Los Angeles, CA 90001 9
186846 09/01/19 16:00 216 Dogwood St, San Francisco, CA 94016 9
186847 09/23/19 07:39 220 12th St, San Francisco, CA 94016 9
186848 09/19/19 17:30 511 Forest St, San Francisco, CA 94016 9
186849 09/30/19 00:18 250 Meadow St, San Francisco, CA 94016 9

Sales City
0 23.90 Dallas (TX)
2 99.99 Boston (MA)
3 600.00 Los Angeles (CA)
4 11.99 Los Angeles (CA)
5 11.99 Los Angeles (CA)
… … …
186845 8.97 Los Angeles (CA)
186846 700.00 San Francisco (CA)
186847 700.00 San Francisco (CA)
186848 379.99 San Francisco (CA)
186849 11.95 San Francisco (CA)

[185950 rows x 9 columns]

0.0.5 Which City had the Highest Sales?

[16]: results = all_data.groupby("City").sum()

[17]: cities = all_data["City"].unique()

plt.bar(cities, results["Sales"])
plt.xticks(cities, rotation=45, size=8)
plt.xlabel("City Name")
plt.ylabel("Sales in USD ($)")
plt.show()

6
 0.0.6 What time should we display advertisements to maximize the likelihood of
customers buying the product?

[18]: all_data["Order Date"] = pd.to_datetime(all_data["Order Date"]) # convert␣

↪datetime format

C:\Users\DELL\AppData\Local\Temp\ipykernel_9116\2228339044.py:1: UserWarning:
Could not infer format, so each element will be parsed individually, falling
back to `dateutil`. To ensure parsing is consistent and as-expected, please
specify a format.
all_data["Order Date"] = pd.to_datetime(all_data["Order Date"]) # convert
datetime format

[19]: all_data.head()

7
[19]: Order ID Product Quantity Ordered Price Each \
0 176558 USB-C Charging Cable 2 11.95
2 176559 Bose SoundSport Headphones 1 99.99
3 176560 Google Phone 1 600.00
4 176560 Wired Headphones 1 11.99
5 176561 Wired Headphones 1 11.99

Order Date Purchase Address Month Sales \

0 2019-04-19 08:46:00 917 1st St, Dallas, TX 75001 4 23.90
2 2019-04-07 22:30:00 682 Chestnut St, Boston, MA 02215 4 99.99
3 2019-04-12 14:38:00 669 Spruce St, Los Angeles, CA 90001 4 600.00
4 2019-04-12 14:38:00 669 Spruce St, Los Angeles, CA 90001 4 11.99
5 2019-04-30 09:27:00 333 8th St, Los Angeles, CA 90001 4 11.99

City
0 Dallas (TX)
2 Boston (MA)
3 Los Angeles (CA)
4 Los Angeles (CA)
5 Los Angeles (CA)

[20]: all_data["Hour"] = all_data["Order Date"].dt.hour

all_data["Minute"] = all_data["Order Date"].dt.minute

[21]: all_data.head()

[21]: Order ID Product Quantity Ordered Price Each \

0 176558 USB-C Charging Cable 2 11.95
2 176559 Bose SoundSport Headphones 1 99.99
3 176560 Google Phone 1 600.00
4 176560 Wired Headphones 1 11.99
5 176561 Wired Headphones 1 11.99

Order Date Purchase Address Month Sales \

0 2019-04-19 08:46:00 917 1st St, Dallas, TX 75001 4 23.90
2 2019-04-07 22:30:00 682 Chestnut St, Boston, MA 02215 4 99.99
3 2019-04-12 14:38:00 669 Spruce St, Los Angeles, CA 90001 4 600.00
4 2019-04-12 14:38:00 669 Spruce St, Los Angeles, CA 90001 4 11.99
5 2019-04-30 09:27:00 333 8th St, Los Angeles, CA 90001 4 11.99

City Hour Minute

0 Dallas (TX) 8 46
2 Boston (MA) 22 30
3 Los Angeles (CA) 14 38
4 Los Angeles (CA) 14 38
5 Los Angeles (CA) 9 27

8
[22]: hours = sorted(all_data["Hour"].unique())
plt.plot(hours, all_data.groupby(["Hour"]).count())
plt.xticks(hours)
plt.grid()
plt.xlabel("Hour")
plt.ylabel("Count of Orders")
plt.show()

#Highest number of orders came on 11 AM & 7 PM (11)

0.0.7 What products sold the most? Why do you think it sold the most?

[23]: product_group = all_data.groupby("Product")

quantity_order = product_group["Quantity Ordered"].sum()
products = [product for product, f in product_group]
plt.bar(products,quantity_order)
plt.ylabel("Quantity Ordered")
plt.xlabel("Product")
plt.xticks(products, rotation="vertical", size=8)
plt.show()

9
[44]: price = all_data.groupby("Product")["Price Each"].mean()

fig,ax1 = plt.subplots()

ax2 = ax1.twinx() # share x axis and create second y axis,␣

↪useful when we show different y axis in common x axis

ax1.bar(products,quantity_order, color="green")
ax2.plot(products,price)

ax1.set_xlabel("Product Name")
ax1.set_ylabel("Quantity Ordered", color="green")

10
ax1.set_xticklabels(products, rotation="vertical", size=8)
plt.title("Quantity Ordered vs Average Price for Each Product")

plt.show()

C:\Users\DELL\AppData\Local\Temp\ipykernel_9116\836746615.py:13: UserWarning:
set_ticklabels() should only be used with a fixed number of ticks, i.e. after
set_ticks() or using a FixedLocator.
ax1.set_xticklabels(products, rotation="vertical", size=8)

#The products with lower prices sold more, while those with higher prices sold less.

11