Collins Macharia Muturi

Data Analysis of Supermarket Data Importing the dependencies import numpy as np import plotly.express as px import plotly.graph_objs as go import plotly.figure_factory as ff from plotly.subplots import make_subplots import pandas as pd import matplotlib.pyplot as plt import seaborn as sns import warnings warnings.filterwarnings('ignore') data = pd.read_csv("C:/Users/Collins PC/Downloads/projects/supermarket_sales/supermarket_sales.csv") data Invoice Branch ID City Customer Gender type Product line Unit Quantity price Total Date Time Payment - - 1/5/2019 13:08 3.8200 80.2200 3/8/2019 10:29 cogs 0 - A Yangon Member Female 1 - C Naypyitaw Normal Female 2 - A Yangon Normal Male Home and 46.33 lifestyle - - 3/3/2019 13:23 Credit 324.31 card 3 - A Yangon Member Male Health and 58.22 beauty - -/27/2019 20:33 Ewallet 465.76 4 - A Yangon Normal Male Sports and 86.31 travel - - Ewallet 604.17 ... ... ... ... ... ... 995 - C Naypyitaw Normal 996 - B Mandalay 997 - A 998 - 999 - Electronic accessories ... 15.28 5 ... 2/8/2019 10:37 Cash ... ... -/29/2019 13:46 Ewallet 76.40 ... ... Male Health and 40.35 beauty 1 2.0175 Normal Female Home and 97.38 lifestyle Yangon Member Male Food and 31.84 beverages 1 1.5920 33.4320 2/9/2019 13:22 Cash 31.84 A Yangon Normal Male Home and 65.82 lifestyle 1 3.2910 -/22/2019 15:33 Cash 65.82 A Yangon Member Female Fashion 88.34 accessories - -/18/2019 13:28 - ... Ewallet 522.83 ... 1000 rows × 17 columns data.info() Health and 74.69 beauty Tax 5% 3/2/2019 17:16 40.35 Ewallet 973.80 Cash 618.38 RangeIndex: 1000 entries, 0 to 999 Data columns (total 17 columns): # Column Non-Null Count --- ------------------0 Invoice ID 1000 non-null 1 Branch 1000 non-null 2 City 1000 non-null 3 Customer type 1000 non-null 4 Gender 1000 non-null 5 Product line 1000 non-null 6 Unit price 1000 non-null 7 Quantity 1000 non-null 8 Tax 5% 1000 non-null 9 Total 1000 non-null 10 Date 1000 non-null 11 Time 1000 non-null 12 Payment 1000 non-null 13 cogs 1000 non-null 14 gross margin percentage 1000 non-null 15 gross income 1000 non-null 16 Rating 1000 non-null dtypes: float64(7), int64(1), object(9) memory usage: 132.9+ KB Dtype ----object object object object object object float64 int64 float64 float64 object object object float64 float64 float64 float64 data.isnull().sum() Invoice ID Branch City Customer type Gender Product line Unit price Quantity Tax 5% Total Date Time Payment cogs gross margin percentage gross income Rating dtype: int64 - Data Visualization import seaborn as sns import matplotlib.pyplot as plt # Set the style of the plot to improve aesthetics sns.set(style="whitegrid") # Get the value counts of the 'City' column city_category_counts = data['City'].value_counts() # Create the bar plot using seaborn plt.figure(figsize=(10, 6)) # Adjust the figure size for better readability sns.barplot(x=city_category_counts.index, y=city_category_counts.values, palette='coolwarm') # Customize the plot further plt.title('City Distribution', fontsize=16) plt.xlabel('City', fontsize=12) plt.ylabel('Count', fontsize=12) plt.xticks(rotation=45, ha='right') # Rotate the x-axis labels for better readability plt.tight_layout() # Adjust layout to prevent label cut-off # Show the plot plt.show() import seaborn as sns import matplotlib.pyplot as plt # Set the style of the plot to improve aesthetics sns.set(style="whitegrid") # Get the value counts of the 'City' column customer_category_counts = data['Customer type'].value_counts() # Create the bar plot using seaborn plt.figure(figsize=(10, 6)) # Adjust the figure size for better readability sns.barplot(x=customer_category_counts.index, y=customer_category_counts.values, palette='coolwarm') # Customize the plot further plt.title('Customer Distribution', fontsize=16) plt.xlabel('Customer Type', fontsize=12) plt.ylabel('Count', fontsize=12) plt.xticks(rotation=45, ha='right') # Rotate the x-axis labels for better readability plt.tight_layout() # Adjust layout to prevent label cut-off # Show the plot plt.show() import seaborn as sns import matplotlib.pyplot as plt # Set the style of the plot to improve aesthetics sns.set(style="whitegrid") # Get the value counts of the 'City' column payment_category_counts = data['Payment'].value_counts() # Create the bar plot using seaborn plt.figure(figsize=(10, 6)) # Adjust the figure size for better readability sns.barplot(x=payment_category_counts.index, y=payment_category_counts.values, palette='coolwarm') # Customize the plot further plt.title('Payment Distribution', fontsize=16) plt.xlabel('Payment Type', fontsize=12) plt.ylabel('Count', fontsize=12) plt.xticks(rotation=45, ha='right') # Rotate the x-axis labels for better readability plt.tight_layout() # Adjust layout to prevent label cut-off # Show the plot plt.show() sns.set(style="whitegrid") # Set color palette to blue shades blue_palette = sns.color_palette('Blues_r') # Visualization 1: Count of customers by gender plt.figure(figsize=(10, 6)) sns.countplot(x='Gender', data=data, palette=blue_palette) plt.title('Count of Customers by Gender') plt.xlabel('Gender') plt.ylabel('Count') plt.show() # Visualization 2: Total sales by branch plt.figure(figsize=(10, 6)) sns.barplot(x='Branch', y='Total', data=data, estimator=sum, palette=blue_palette) plt.title('Total Sales by Branch') plt.xlabel('Branch') plt.ylabel('Total Sales') plt.show() # Visualization 3: Distribution of product line sales plt.figure(figsize=(10, 6)) sns.boxplot(x='Product line', y='Total', data=data, palette=blue_palette) plt.title('Distribution of Product Line Sales') plt.xlabel('Product Line') plt.ylabel('Total Sales') plt.xticks(rotation=45) plt.show() # Visualization 4: Total sales distribution plt.figure(figsize=(10, 6)) sns.histplot(data['Total'], kde=True, color='blue', bins=20) plt.title('Total Sales Distribution') plt.xlabel('Total Sales') plt.ylabel('Frequency') plt.show() # Visualization: Gross Income by Product plt.figure(figsize=(10, 6)) sns.barplot(x='Product line', y='gross income', data=data, estimator=sum, palette=blue_palette) plt.title('Gross Income Per Product') plt.xlabel('Product') plt.ylabel('Gross Income') plt.xticks(rotation=45, ha='right') plt.tight_layout() plt.show() data Invoice Branch ID City Customer Gender type Product line Unit Quantity price Health and 74.69 beauty Tax 5% Total Date Time Payment - - 1/5/2019 13:08 3.8200 80.2200 3/8/2019 10:29 cogs 0 - A Yangon Member Female 1 - C Naypyitaw Normal Female 2 - A Yangon Normal Male Home and 46.33 lifestyle - - 3/3/2019 13:23 Credit 324.31 card 3 - A Yangon Member Male Health and 58.22 beauty - -/27/2019 20:33 Ewallet 465.76 4 - A Yangon Normal Male Sports and 86.31 travel - - Ewallet 604.17 ... ... ... ... ... ... 995 - C Naypyitaw Normal 996 - B Mandalay 997 - A 998 - 999 - Electronic accessories 5 ... ... ... Male Health and 40.35 beauty 1 2.0175 -/29/2019 13:46 Ewallet Normal Female Home and 97.38 lifestyle Yangon Member Male Food and 31.84 beverages 1 1.5920 33.4320 2/9/2019 13:22 Cash 31.84 A Yangon Normal Male Home and 65.82 lifestyle 1 3.2910 -/22/2019 15:33 Cash 65.82 A Yangon Member Female Fashion 88.34 accessories - -/18/2019 13:28 - ... 76.40 ... data['Time'].value_counts() ... 2/8/2019 10:37 Cash ... 1000 rows × 17 columns ... 15.28 Ewallet 522.83 3/2/2019 17:16 40.35 Ewallet 973.80 Cash 618.38 Time 19:48 14:42 17:38 17:16 11:40 13:26 11:17 14:57 17:53 19:12 Name: 7 7 6 5 5 .. 1 1 1 1 1 count, Length: 506, dtype: int64 data['Product line'].value_counts() Product line Fashion accessories Food and beverages Electronic accessories Sports and travel Home and lifestyle Health and beauty Name: count, dtype: int64 - import matplotlib.pyplot as plt # store value counts in a variable called `product_line_counts` product_line_counts = data['Product line'].value_counts() # Plot the data plt.figure(figsize=(10, 8)) product_line_counts.plot(kind='barh', color='skyblue') # Add labels and title plt.xlabel('Number of Products') plt.ylabel('Product Line') plt.title('Frequency of Product Lines') # Show the plot plt.tight_layout() plt.show() Product Line Analysis Health and beauty data_health = data[data['Product line']=="Health and beauty"] data_health Invoice Branch ID City Customer Product Gender type line Unit Quantity price Tax 5% Total Date Time Payment cogs 0 - A Yangon Member Female Health and 74.69 beauty - 1/5/2019 13:08 Ewallet 522.83 3 - A Yangon Member Male Health and 58.22 beauty -/27/2019 20:33 Ewallet 465.76 8 - A Yangon Member Female Health and 36.26 beauty 2 14 - A Yangon Normal Female Health and 71.38 beauty -/29/2019 19:21 Cash 713.80 16 - A Yangon Member Female Health and 68.93 beauty -/11/2019 11:03 Credit 482.51 card ... ... ... ... ... ... 983 - C Naypyitaw Normal Male Health and 99.96 beauty -/23/2019 10:33 986 - B Mandalay Normal Female Health and 14.76 beauty 2 987 - B Mandalay Member Male Health and 62.00 beauty - 1/3/2019 19:08 Credit 496.00 card 989 - B Mandalay Member Male Health and 75.37 beauty -/28/2019 15:46 Credit 602.96 card 995 - C Naypyitaw Normal Male Health and 40.35 beauty 1 ... ... 3.6260 ... ... 1.4760 2.0175 152 rows × 17 columns import plotly.offline as pyo import plotly.express as px # Ensure the notebook mode is enabled pyo.init_notebook_mode() # Create the box plot fig = px.box(x=data_health['Rating'], labels={"x": "Rating"}, title="5-Number-Summary Plot of Ratings (Health & Beauty)") # Display the plot in the notebook pyo.iplot(fig) -/10/2019 17:15 ... ... ... -/18/2019 14:42 -/29/2019 13:46 Credit card ... 72.52 ... Cash 699.72 Ewallet Ewallet 29.52 40.35 5-Number-Summary Plot of Ratings (Health & Beauty) 4 5 6 7 8 9 Rating # Visualization: Count of customers by gender plt.figure(figsize=(10, 6)) sns.countplot(x='Gender', data=data_health, palette=blue_palette) plt.title('Number of Health and beauty Customers by Gender') plt.xlabel('Gender') plt.ylabel('Count') plt.show() Fashion accessories data_fashion = data[data['Product line']=="Fashion accessories"] data_fashion 10 Invoice Branch ID City Customer Gender type Product line Unit Quantity price Tax 5% Total Date Time Payment cogs 10 - B Mandalay Member Female Fashion 14.48 accessories 4 2.8960 60.8160 2/6/2019 18:07 Ewallet 57.92 26 - B Mandalay Normal Male Fashion 33.52 accessories 1 1.6760 35.1960 2/8/2019 15:31 Cash 33.52 27 - A Yangon Normal Female Fashion 87.67 accessories 2 -/10/2019 12:17 Credit 175.34 card 30 - B Mandalay Normal Male Fashion 94.13 accessories -/25/2019 19:39 Credit 470.65 card 49 - C Naypyitaw Member Female Fashion 82.63 accessories -/19/2019 17:08 Ewallet 826.30 ... ... ... ... ... 974 - C Naypyitaw Normal 975 - B Mandalay 985 - B 993 - 999 - ... ... ... ... Male Fashion 86.13 accessories 2 - 2/7/2019 17:59 Member Male Fashion 49.92 accessories 2 - 3/6/2019 11:55 Mandalay Normal Female Fashion 63.71 accessories - 2/7/2019 19:30 Ewallet 318.55 B Mandalay Normal Male Fashion 17.49 accessories -/22/2019 18:35 Ewallet 174.90 A Yangon Member Female Fashion 88.34 accessories -/18/2019 13:28 Cash 618.38 10 ... 178 rows × 17 columns import plotly.offline as pyo import plotly.express as px # Ensure the notebook mode is enabled pyo.init_notebook_mode() # Create the box plot fig = px.box(x=data_fashion['Rating'], labels={"x": "Rating"}, title="5-Number-Summary Plot of Ratings (Fashion accessories)") # Display the plot in the notebook pyo.iplot(fig) # Visualization: Count of customers by gender plt.figure(figsize=(10, 6)) ... ... ... ... ... Cash 172.26 Credit card 99.84 sns.countplot(x='Gender', data=data_fashion, palette=blue_palette) plt.title('Number of Fashion accessories Customers by Gender') plt.xlabel('Gender') plt.ylabel('Count') plt.show() Sports and travel data_sports = data[data['Product line']=="Sports and travel"] data_sports Invoice Branch ID City Customer Product Gender type line Unit Quantity price Tax 5% Total Date Time Payment cogs perc 4 - A Yangon Normal Male Sports and 86.31 travel - 2/8/2019 10:37 Ewallet 604.17 15 - B Mandalay Member Female Sports and 93.72 travel -/15/2019 16:19 Cash 562.32 17 - A Yangon Normal Male Sports and 72.61 travel - 1/1/2019 10:39 Credit 435.66 card 24 - A Yangon Member Male Sports and 88.63 travel - 3/2/2019 17:36 Ewallet 265.89 31 - B Mandalay Member Male Sports and 78.07 travel -/28/2019 12:43 Cash 702.63 ... ... ... ... ... 926 - B Mandalay Member 929 - B Mandalay 937 - A 982 - A 991 - ... ... ... ... ... ... ... ... Male Sports and 88.31 travel 1 4.4155 -/15/2019 17:38 Credit card 88.31 Normal Male Sports and 25.31 travel 2 2.5310 53.1510 Ewallet 50.62 Yangon Normal Female Sports and 89.48 travel -/30/2019 10:18 Cash 447.40 Yangon Member Female Sports and 97.48 travel -/14/2019 14:19 Ewallet 877.32 B Mandalay Normal Female Sports and 76.60 travel -/24/2019 18:10 Ewallet 766.00 166 rows × 17 columns import plotly.offline as pyo import plotly.express as px # Ensure the notebook mode is enabled pyo.init_notebook_mode() # Create the box plot fig = px.box(x=data_sports['Rating'], labels={"x": "Rating"}, title="5-Number-Summary Plot of Ratings (Sports and travel)") # Display the plot in the notebook pyo.iplot(fig) ... ... 3/2/2019 19:26 # Visualization: Count of customers by gender plt.figure(figsize=(10, 6)) sns.countplot(x='Gender', data=data_sports, palette=blue_palette) plt.title('Number of Sports and travel Customers by Gender') plt.xlabel('Gender') plt.ylabel('Count') plt.show() Food and beverages data_food = data[data['Product line']=="Food and beverages"] data_food Invoice Branch ID City Customer Gender type Product line Unit Quantity price 9 - B Mandalay Member Female Food and 54.84 beverages 13 - A Yangon Normal Male Food and 43.19 beverages 18 - A Yangon Normal Male Food and 54.67 beverages 3 28 - B Mandalay Normal Female 34 - C Naypyitaw Member Female ... ... ... ... ... ... 977 - B Mandalay Member 979 - B Mandalay 980 - C Naypyitaw 990 - A 997 - A 3 Tax 5% Total Date Time Payment -/20/2019 13:27 Credit 164.52 card 2/7/2019 16:48 Ewallet 431.90 -/21/2019 18:00 Credit 164.01 card Food and 88.36 beverages -/25/2019 19:48 Cash 441.80 Food and 99.42 beverages - ... - cogs ... ... Male Food and 26.60 beverages 6 -/26/2019 15:10 Normal Female Food and 67.77 beverages 1 3.3885 Member Male Food and 59.59 beverages -/19/2019 12:46 Cash 238.36 Yangon Normal Female Food and 56.56 beverages -/22/2019 19:06 Credit 282.80 card Yangon Member Male Food and 31.84 beverages 1 174 rows × 17 columns import plotly.offline as pyo import plotly.express as px # Ensure the notebook mode is enabled pyo.init_notebook_mode() # Create the box plot fig = px.box(x=data_food['Rating'], labels={"x": "Rating"}, title="5-Number-Summary Plot of Ratings (Food and beverages)") # Display the plot in the notebook pyo.iplot(fig) # Visualization: Count of customers by gender plt.figure(figsize=(10, 6)) 71.1585 33.4320 ... ... Ewallet 397.68 ... 1.5920 ... 2/6/2019 10:42 2/4/2019 20:43 2/9/2019 13:22 ... ... Ewallet 159.60 Credit card Cash 67.77 31.84 sns.countplot(x='Gender', data=data_food, palette=blue_palette) plt.title('Number of Food and beverages Customers by Gender') plt.xlabel('Gender') plt.ylabel('Count') plt.show() Home and lifestyle data_home = data[data['Product line']=="Home and lifestyle"] data_home Invoice Branch ID City Customer Product Gender type line Unit Quantity price Tax 5% Total - Date Time Payment cogs 2 - A Yangon Normal Male Home and 46.33 lifestyle - 7 - C Naypyitaw Normal Female Home and 73.56 lifestyle - 19 - B Mandalay Normal Female Home and 40.30 lifestyle 2 4.0300 -/11/2019 15:30 Ewallet 80.60 22 - B Mandalay Normal Male Home and 33.20 lifestyle 2 3.3200 -/15/2019 12:20 Credit card 66.40 25 - A Yangon Member Female Home and 52.59 lifestyle - -/22/2019 19:20 ... ... ... ... ... ... 967 - A Yangon Member Male Home and 81.01 lifestyle - -/13/2019 12:55 Credit 243.03 card 971 - B Mandalay Member Male Home and 36.91 lifestyle - -/10/2019 13:51 Ewallet 258.37 973 - A Yangon Normal Male Home and 80.08 lifestyle - -/11/2019 15:29 Cash 240.24 996 - B Mandalay Normal Female Home and 97.38 lifestyle 998 - A Yangon Normal Male Home and 65.82 lifestyle ... ... ... ... Credit 324.31 card -/24/2019 11:38 Ewallet 735.60 ... - 1 3.2910 160 rows × 17 columns import plotly.offline as pyo import plotly.express as px # Ensure the notebook mode is enabled pyo.init_notebook_mode() # Create the box plot fig = px.box(x=data_home['Rating'], labels={"x": "Rating"}, title="5-Number-Summary Plot of Ratings (Home and lifestyle)") # Display the plot in the notebook pyo.iplot(fig) 3/3/2019 13:23 ... ... 3/2/2019 17:16 -/22/2019 15:33 Credit 420.72 card ... ... Ewallet 973.80 Cash 65.82 # Visualization: Count of customers by gender plt.figure(figsize=(10, 6)) sns.countplot(x='Gender', data=data_home, palette=blue_palette) plt.title('Number of Home and lifestyle Customers by Gender') plt.xlabel('Gender') plt.ylabel('Count') plt.show() Electronic accessories data_electronics = data[data['Product line']=="Electronic accessories"] data_electronics Invoice Branch ID City Customer Gender type Product line Unit Quantity price Tax 5% Total 3.8200 80.2200 Date Time Payment cogs 1 - C Naypyitaw Normal Female Electronic accessories 15.28 5 5 - C Naypyitaw Normal Male Electronic accessories 85.39 -/25/2019 18:30 Ewallet 597.73 6 - A Yangon Member Female Electronic accessories 68.84 -/25/2019 14:36 Ewallet 413.04 11 - B Mandalay Member Male Electronic accessories 25.51 4 3/9/2019 17:03 Cash 102.04 12 - A Yangon Normal Female Electronic accessories 46.95 -/12/2019 10:25 Ewallet 234.75 ... ... ... ... ... ... ... ... ... ... 978 - B Mandalay Normal Female Electronic accessories 25.45 1 1.2725 984 - C Naypyitaw Normal Male Electronic accessories 96.37 - 988 - C Naypyitaw Member Male Electronic accessories 82.34 992 - A Yangon Normal Male Electronic accessories 58.03 2 -/10/2019 20:46 Ewallet 116.06 994 - C Naypyitaw Member Female Electronic accessories 60.95 1 3.0475 Ewallet - ... 76.40 ... ... -/10/2019 18:10 Credit card 25.45 1/9/2019 11:40 Cash 674.59 -/29/2019 19:12 Ewallet 823.40 -/18/2019 11:40 import plotly.offline as pyo import plotly.express as px # Ensure the notebook mode is enabled pyo.init_notebook_mode() # Create the box plot fig = px.box(x= data_electronics['Rating'], labels={"x": "Rating"}, title="5-Number-Summary Plot of Ratings (Electronic accessories)") # Visualization: Count of customers by gender plt.figure(figsize=(10, 6)) ... Cash ... 170 rows × 17 columns # Display the plot in the notebook pyo.iplot(fig) 3/8/2019 10:29 60.95 sns.countplot(x='Gender', data=data_electronics, palette=blue_palette) plt.title('Number of Electronic accessories Customers by Gender') plt.xlabel('Gender') plt.ylabel('Count') plt.show() Branches A branch_A = data[data['Branch']=="A"] branch_A Invoice Branch ID City Customer Gender type Product line Unit Quantity price Tax 5% Total Date Time Payment cogs 0 - A Yangon Member Female Health and 74.69 beauty - 1/5/2019 13:08 Ewallet 522.83 2 - A Yangon Normal Male Home and 46.33 lifestyle - 3/3/2019 13:23 Credit 324.31 card 3 - A Yangon Member Male Health and 58.22 beauty -/27/2019 20:33 Ewallet 465.76 4 - A Yangon Normal Male Sports and 86.31 travel - 2/8/2019 10:37 Ewallet 604.17 6 - A Yangon Member Female Electronic 68.84 accessories -/25/2019 14:36 Ewallet 413.04 ... ... ... ... ... 990 - A Yangon Normal Female Food and 56.56 beverages 992 - A Yangon Normal Male Electronic 58.03 accessories 2 -/10/2019 20:46 997 - A Yangon Member Male Food and 31.84 beverages 1 1.5920 33.4320 2/9/2019 13:22 Cash 31.84 998 - A Yangon Normal Male Home and 65.82 lifestyle 1 3.2910 -/22/2019 15:33 Cash 65.82 999 - A Yangon Member Female Fashion 88.34 accessories ... ... ... ... ... ... ... ... -/22/2019 19:06 -/18/2019 13:28 ... ... Credit 282.80 card Ewallet 116.06 Cash 618.38 340 rows × 17 columns # Visualization: Gross Income by Product plt.figure(figsize=(10, 6)) sns.barplot(x='Product line', y='gross income', data=branch_A, estimator=sum, palette=blue_palette) plt.title('Gross Income Per Product Branch A') plt.xlabel('Product') plt.ylabel('Gross Income') plt.xticks(rotation=45, ha='right') plt.tight_layout() plt.show() fig = px.bar(branch_A, x = 'Product line', y = 'Rating', hover_data = ['gross income'],color = 'Gender', height = 400 fig.show() import matplotlib.pyplot as plt # store value counts in a variable called `product_line_counts` product_line_counts = branch_A['Product line'].value_counts() # Plot the data plt.figure(figsize=(10, 8)) product_line_counts.plot(kind='barh', color='skyblue') # Add labels and title plt.xlabel('Number of Products Branch A') plt.ylabel('Product Line') plt.title('Frequency of Product Lines') # Show the plot plt.tight_layout() plt.show() B branch_B = data[data['Branch']=="B"] branch_B Invoice Branch ID City Customer Gender type Product line Unit Quantity price Tax 5% Total Date Time Payment cogs 9 - B Mandalay Member Female Food and 54.84 beverages 3 8.226 10 - B Mandalay Member Female Fashion 14.48 accessories 4 2.896 60.816 2/6/2019 18:07 11 - B Mandalay Member Male Electronic accessories 4 5.102 107.142 3/9/2019 17:03 Cash 102.04 15 - B Mandalay Member Female Sports and 93.72 travel 6 28.116 -/15/2019 16:19 Cash 562.32 19 - B Mandalay Normal Female Home and 40.30 lifestyle 2 4.030 ... ... ... ... ... ... ... ... ... 987 - B Mandalay Member Male Health and 62.00 beauty 8 24.800 520.800 1/3/2019 19:08 Credit 496.00 card 989 - B Mandalay Member Male Health and 75.37 beauty 8 30.148 -/28/2019 15:46 Credit 602.96 card 991 - B Mandalay Normal Female Sports and 76.60 travel - -/24/2019 18:10 Ewallet 766.00 993 - B Mandalay Normal Male Fashion 17.49 accessories 10 -/22/2019 18:35 Ewallet 174.90 996 - B Mandalay Normal Female Home and 97.38 lifestyle ... 332 rows × 17 columns 25.51 ... 8.745 -/20/2019 13:27 84.630 3/11/2019 15:30 - ... ... 3/2/2019 17:16 Credit 164.52 card Ewallet 57.92 Ewallet 80.60 ... ... Ewallet 973.80 # Visualization: Gross Income by Product plt.figure(figsize=(10, 6)) sns.barplot(x='Product line', y='gross income', data=branch_B , estimator=sum, palette=blue_palette) plt.title('Gross Income Per Product Branch B') plt.xlabel('Product') plt.ylabel('Gross Income') plt.xticks(rotation=45, ha='right') plt.tight_layout() plt.show() fig = px.bar(branch_B, x = 'Product line', y = 'Rating', hover_data = ['gross income'],color = 'Gender', height = 400 fig.show() import matplotlib.pyplot as plt # store value counts in a variable called `product_line_counts` product_line_counts = branch_B['Product line'].value_counts() # Plot the data plt.figure(figsize=(10, 8)) product_line_counts.plot(kind='barh', color='skyblue') # Add labels and title plt.xlabel('Number of Products Branch B') plt.ylabel('Product Line') plt.title('Frequency of Product Lines') # Show the plot plt.tight_layout() plt.show() C branch_C = data[data['Branch']=="C"] branch_C Invoice Branch ID City Customer Gender type Product line Unit Quantity price Tax 5% Total 3.8200 80.2200 Date Time Payment cogs 1 - C Naypyitaw Normal Female Electronic accessories 15.28 5 5 - C Naypyitaw Normal Male Electronic accessories 85.39 -/25/2019 18:30 Ewallet 597.73 7 - C Naypyitaw Normal Female Home and 73.56 lifestyle -/24/2019 11:38 Ewallet 735.60 20 - C Naypyitaw Member Male -/25/2019 11:24 Ewallet 430.20 34 - C Naypyitaw Member Female - Ewallet 397.68 ... ... ... ... ... 983 - C Naypyitaw Normal Male 984 - C Naypyitaw Normal Male Electronic accessories 96.37 988 - C Naypyitaw Member Male Electronic accessories 82.34 994 - C Naypyitaw Member Female Electronic accessories 60.95 1 3.0475 -/18/2019 11:40 Ewallet 60.95 995 - C Naypyitaw Normal Male Health and 40.35 beauty 1 2.0175 -/29/2019 13:46 Ewallet 40.35 ... Electronic accessories 86.04 Food and 99.42 beverages ... ... Health and 99.96 beauty ... ... ... 3/8/2019 10:29 2/6/2019 10:42 ... ... Cash ... 76.40 ... -/23/2019 10:33 Cash 699.72 - 1/9/2019 11:40 Cash 674.59 -/29/2019 19:12 Ewallet 823.40 328 rows × 17 columns # Visualization: Gross Income by Product plt.figure(figsize=(10, 6)) sns.barplot(x='Product line', y='gross income', data=branch_C , estimator=sum, palette=blue_palette) plt.title('Gross Income Per Product Branch C') plt.xlabel('Product') plt.ylabel('Gross Income') plt.xticks(rotation=45, ha='right') plt.tight_layout() plt.show() fig = px.bar(branch_B, x = 'Product line', y = 'Rating', hover_data = ['gross income'],color = 'Gender', height = 400 fig.show() import matplotlib.pyplot as plt # store value counts in a variable called `product_line_counts` product_line_counts = branch_C['Product line'].value_counts() # Plot the data plt.figure(figsize=(10, 8)) product_line_counts.plot(kind='barh', color='skyblue') # Add labels and title plt.xlabel('Number of Products Branch C') plt.ylabel('Product Line') plt.title('Frequency of Product Lines') # Show the plot plt.tight_layout() plt.show() Date Analysis import pandas as pd # Function to handle multiple date formats def convert_date(date_str): formats = ['%Y-%m-%d %H:%M:%S', '%d/%m/%y %H:%M', '%Y-%m-%d', '%d/%m/%y'] for fmt in formats: try: # Try to convert the date using one of the formats return pd.to_datetime(date_str, format=fmt) except (ValueError, TypeError): continue return date_str # Return original value if no format matches # Apply the conversion function to the 'Date' column data['Date'] = data['Date'].apply(convert_date) data # Add other formats if needed Invoice Branch ID City Customer Gender type Product line Unit Quantity price Health and 74.69 beauty Tax 5% Total Date Time Payment - - 1/5/2019 13:08 3.8200 80.2200 3/8/2019 10:29 cogs 0 - A Yangon Member Female 1 - C Naypyitaw Normal Female 2 - A Yangon Normal Male Home and 46.33 lifestyle - - 3/3/2019 13:23 Credit 324.31 card 3 - A Yangon Member Male Health and 58.22 beauty - -/27/2019 20:33 Ewallet 465.76 4 - A Yangon Normal Male Sports and 86.31 travel - - Ewallet 604.17 ... ... ... ... ... ... 995 - C Naypyitaw Normal 996 - B Mandalay 997 - A 998 - 999 - Electronic accessories ... 15.28 5 Ewallet 522.83 Cash 2/8/2019 10:37 ... ... ... ... ... ... Male Health and 40.35 beauty 1 2.0175 -/29/2019 13:46 Ewallet Normal Female Home and 97.38 lifestyle Yangon Member Male Food and 31.84 beverages 1 1.5920 33.4320 2/9/2019 13:22 Cash 31.84 A Yangon Normal Male Home and 65.82 lifestyle 1 3.2910 -/22/2019 15:33 Cash 65.82 A Yangon Member Female Fashion 88.34 accessories - -/18/2019 13:28 - ... 76.40 3/2/2019 17:16 40.35 Ewallet 973.80 Cash 618.38 1000 rows × 17 columns data['Date'] = pd.to_datetime(data['Date']) # Extract year, month, day, and weekday data['year'] = data['Date'].dt.year data['month'] = data['Date'].dt.month data['day'] = data['Date'].dt.day data['weekday'] = data['Date'].dt.weekday data Invoice Branch ID City Customer Gender type 0 - A Yangon Member Female 1 - C Naypyitaw Normal Female 2 - A Yangon Normal Male 3 - A Yangon Member 4 - A Yangon ... ... ... 995 Product line Unit Quantity price Health and 74.69 beauty Electronic accessories Time Payment cogs percen - Total ... - ... 13:08 3.8200 80.2200 ... 10:29 Home and 46.33 lifestyle - Male Health and 58.22 beauty Normal Male Sports and 86.31 travel ... ... ... - C Naypyitaw Normal 996 - B Mandalay 997 - A 998 - 999 - Ewallet- 4.76 - ... 13:23 Credit 324.31 card 4.76 - - ... 20:33 Ewallet 465.76 4.76 - - ... 10:37 Ewallet 604.17 4.76 ... ... Male Health and 40.35 beauty 1 2.0175 Normal Female Home and 97.38 lifestyle Yangon Member Male Food and 31.84 beverages 1 1.5920 33.4320 ... 13:22 Cash 31.84 4.76 A Yangon Normal Male Home and 65.82 lifestyle 1 3.2910 69.1110 ... 15:33 Cash 65.82 4.76 A Yangon Member Female Fashion 88.34 accessories - - ... 13:28 Cash 618.38 4.76 import calendar # Convert numerical month to month name ... ... Cash 4.76 ... 1000 rows × 21 columns ... 15.28 Tax 5% ... ... ... 42.3675 ... 13:46 Ewallet 40.35 4.76 Ewallet 973.80 4.76 - ... 17:16 data['month_name'] = data['month'].apply(lambda x: calendar.month_name[x]) data Invoice Branch ID City Customer Gender type 0 - A Yangon Member Female 1 - C Naypyitaw Normal Female 2 - A Yangon Normal Male 3 - A Yangon Member 4 - A Yangon ... ... ... 995 Product line Unit Quantity price Health and 74.69 beauty Electronic accessories - cogs gross margin percentage Ewallet 522.83 - Total ... Payment - ... 3.8200 80.2200 ... Home and 46.33 lifestyle - Male Health and 58.22 beauty Normal Male Sports and 86.31 travel ... ... ... - C Naypyitaw Normal 996 - B Mandalay 997 - A 998 - 999 - ... 15.28 Tax 5% Cash 76.40 - - ... Credit 324.31 card - - - ... Ewallet 465.76 - - - ... Ewallet 604.17 - ... ... ... ... ... ... ... ... Male Health and 40.35 beauty 1 2.0175 42.3675 ... Ewallet 40.35 - Normal Female Home and 97.38 lifestyle Ewallet 973.80 - Yangon Member Male Food and 31.84 beverages 1 1.5920 33.4320 ... Cash 31.84 - A Yangon Normal Male Home and 65.82 lifestyle 1 3.2910 69.1110 ... Cash 65.82 - A Yangon Member Female Fashion 88.34 accessories - - ... Cash 618.38 - - ... 1000 rows × 22 columns # Visualization: Total sales by Month plt.figure(figsize=(10, 6)) sns.barplot(x='month_name', y='Total', data = data , estimator=sum, palette=blue_palette) plt.title('Total Sales Per Month') plt.xlabel('Product') plt.ylabel('Gross Income') plt.xticks(rotation=45, ha='right') plt.tight_layout() plt.show() data['month_name'].value_counts() month_name January 352 March 345 February 303 Name: count, dtype: int64 import calendar # Convert numerical weekday to day name data['day_name'] = data['weekday'].apply(lambda x: calendar.day_name[x]) data Invoice Branch ID City Customer Gender type Product line Unit Quantity price Health and 74.69 beauty Tax 5% Total ... cogs gross margin percentage gross income 0 - A Yangon Member Female 1 - C Naypyitaw Normal Female 2 - A Yangon Normal Male Home and 46.33 lifestyle - - ... 324.31 - 3 - A Yangon Member Male Health and 58.22 beauty - - ... 465.76 - 4 - A Yangon Normal Male Sports and 86.31 travel - - ... 604.17 - ... ... ... ... ... ... 995 - C Naypyitaw Normal 996 - B Mandalay 997 - A 998 - 999 - Electronic accessories ... 15.28 - 3.8200 - ..- ... 76.40 - 3.8200 ... ... ... ... ... ... ... ... Male Health and 40.35 beauty 1 2.0175 42.3675 ... 40.35 - 2.0175 Normal Female Home and 97.38 lifestyle Yangon Member Male Food and 31.84 beverages 1 1.5920 33.4320 ... 31.84 - 1.5920 A Yangon Normal Male Home and 65.82 lifestyle 1 3.2910 69.1110 ... 65.82 - 3.2910 A Yangon Member Female Fashion 88.34 accessories - ... 973.80 - - ... 618.38 1000 rows × 23 columns # Visualization: Total sales by Month plt.figure(figsize=(10, 6)) sns.barplot(x='day_name', y='Total', data = data , estimator=sum, palette=blue_palette) plt.title('Total Quarterly Sales Per Day') plt.xlabel('Day') plt.ylabel('Total Sales') plt.xticks(rotation=45, ha='right') plt.tight_layout() plt.show() - - # Visualization: Total sales by Month plt.figure(figsize=(10, 6)) sns.barplot(x='day_name', y='gross income', data = data , estimator=sum, palette=blue_palette) plt.title('Total Quarterly Income Per Day') plt.xlabel('Day') plt.ylabel('Total Income') plt.xticks(rotation=45, ha='right') plt.tight_layout() plt.show() def generate_rating_df(df): rating_df = data.groupby(['day_name','Rating']).agg({'Invoice ID': 'count'}).reset_index() rating_df = rating_df[rating_df['Invoice ID'] != 0] rating_df.columns = ['day_name','Rating', 'counts'] rating_df = rating_df.sort_values('Rating') return rating_df rating_df = generate_rating_df(data) fig = px.bar(rating_df, x='day_name', y='counts', color='Rating') fig.update_traces(textposition='auto', textfont_size=20) fig.update_layout(barmode='stack') import plotly.express as px import plotly.io as pio # Function to generate a rating dataframe def generate_rating_df(df): rating_df = df.groupby(['day_name', 'Rating']).agg({'Invoice ID': 'count'}).reset_index() rating_df = rating_df[rating_df['Invoice ID'] != 0] rating_df.columns = ['day_name', 'Rating', 'counts'] rating_df = rating_df.sort_values('Rating') return rating_df # Generate the rating dataframe rating_df = generate_rating_df(data) # Create the bar plot fig = px.bar(rating_df, x='day_name', y='counts', color='Rating') # Update trace styles fig.update_traces(textposition='auto', textfont_size=20) # Set layout options for stacked bars fig.update_layout(barmode='stack') # Show interactive plot fig.show() # Export the plot as a static image for GitHub or PDF # Ensure you have kaleido installed: `pip install -U kaleido` fig.write_image("stacked_bar_ratings_per_day.png") # Save as PNG # Optional: Save as PDF fig.write_image("stacked_bar_ratings_per_day.pdf") # Save as PDF import plotly.express as px import plotly.io as pio import pandas as pd # Function to generate rating DataFrame def generate_rating_df(df): # Group data by 'day_name' and 'Rating', and count the occurrences of 'Invoice ID' rating_df = df.groupby(['day_name', 'Rating']).agg({'Invoice ID': 'count'}).reset_index() rating_df = rating_df[rating_df['Invoice ID'] != 0] rating_df.columns = ['day_name', 'Rating', 'counts'] rating_df = rating_df.sort_values('Rating') return rating_df # Generate rating_df using your data rating_df = generate_rating_df(data) # Create bar chart figure fig = px.bar(rating_df, x='day_name', y='counts', color='Rating') # Update chart layout and traces fig.update_traces(textposition='auto', textfont_size=20) fig.update_layout(barmode='stack', title="Ratings per Day", xaxis_title="Day of the Week", yaxis_title="Counts", font=dict(size=14)) # Convert to a printable HTML file html_content = pio.to_html(fig, full_html=False, include_plotlyjs='cdn') # Write the HTML content to a file with open("rating_chart.html", "w") as f: f.write(html_content) print("HTML file successfully generated for printing.") HTML file successfully generated for printing. fig = px.scatter(data_frame = data, x="day_name", y="gross income", color="Gender", size='Rating', hover_data=['Total'], marginal_x="histogram", marginal_y="box",) fig.update_layout(title_text=" Gross Income Per Day ", titlefont={'size': 24, 'family':'Serif'}, width=1000, height=550, ) fig.show() import plotly.express as px import plotly.io as pio # Create the scatter plot fig = px.scatter(data_frame=data, x="day_name", y="gross income", color="Gender", size='Rating', hover_data=['Total'], marginal_x="histogram", marginal_y="box") # Update layout fig.update_layout(title_text=" Gross Income Per Day ", titlefont={'size': 24, 'family': 'Serif'}, width=1000, height=550) # Show interactive plot fig.show() # Export the plot as a static image for GitHub or PDF # Ensure you have kaleido installed: `pip install -U kaleido` fig.write_image("gross_income_per_day.png") # Save as PNG # Optional: Save as PDF fig.write_image("gross_income_per_day.pdf") # Save as PDF fig = px.histogram(data, x='Rating',height=500,width=900,template='simple_white', color='Product line', # adding categorical column color_discrete_sequence=['purple','pink','aliceblue','blanchedalmond','darkolivegreen','darkslateg fig.update_layout(title={'text':'Histogram of Ratings Per Product Line','font':{'size':25}} ,title_font_family="Times New Roman", title_font_color="darkgrey", title_x=0.2) fig.update_layout( font_family='classic-roman', font_color= 'grey', yaxis_title={'text': " count", 'font': {'size':18}}, xaxis_title={'text': " Rating", 'font': {'size':18}} ) fig.show() import plotly.express as px import plotly.io as pio # Create the histogram plot fig = px.histogram(data, x='Rating', height=500, width=900, template='simple_white', color='Product line', # Adding categorical column color_discrete_sequence=['purple', 'pink', 'aliceblue', 'blanchedalmond', 'darkolivegreen', 'darkslategray']) # Update layout fig.update_layout( title={'text': 'Histogram of Ratings Per Product Line', 'font': {'size': 25}}, title_font_family="Times New Roman", title_font_color="darkgrey", title_x=0.2, font_family='classic-roman', font_color='grey', yaxis_title={'text': "Count", 'font': {'size': 18}}, xaxis_title={'text': "Rating", 'font': {'size': 18}} ) # Show interactive plot fig.show() # Export the plot as a static image for GitHub or PDF # Ensure you have kaleido installed: `pip install -U kaleido` fig.write_image("histogram_of_ratings_per_product_line.png") # Save as PNG # Optional: Save as PDF fig.write_image("histogram_of_ratings_per_product_line.pdf") # Save as PDF