NAME – DIPANSHU REGRESTATION NO -12217249

COURSE CODE-CAP 793

PART-1 Data Preparation and Basic Plots

Q1- - Create a DataFrame with the following columns: `Month`, `Product_A_Sales`,
`Product_B_Sales`, `Product_C_Sales`.

ANS 1-

import pandas as pd

data = {

'Month': ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October',
'November', 'December'],

'Product_A_Sales': [5000, 6000, 7000, 8000, 7500, 8200, 7800, 8400, 8200, 8600, 8800, 9000],

'Product_B_Sales': [7000, 6500, 7200, 6800, 7000, 7300, 7100, 7600, 7200, 7300, 7400, 7500],

'Product_C_Sales': [8000, 7000, 6800, 7500, 8200, 7900, 8500, 8100, 7900, 7800, 8000, 8300]

df = pd.DataFrame(data)

df['Total_Sales'] = df[['Product_A_Sales', 'Product_B_Sales', 'Product_C_Sales']].sum(axis=1)

df['Average_Sales'] = df[['Product_A_Sales', 'Product_B_Sales', 'Product_C_Sales']].mean(axis=1)

print(df)
2- . Line Plot:

- Create a line plot to display the sales trends of Product A, Product B, and Product C over the
months using Matplotlib or Seaborn.

- Ensure the plot has a title, labeled axes, and a legend.

ANS 2-

import pandas as pd

import matplotlib.pyplot as plt

data = {

'Month': ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October',
'November', 'December'],

'Product_A_Sales': [5000, 6000, 7000, 8000, 7500, 8200, 7800, 8400, 8200, 8600, 8800, 9000],

'Product_B_Sales': [7000, 6500, 7200, 6800, 7000, 7300, 7100, 7600, 7200, 7300, 7400, 7500],

'Product_C_Sales': [8000, 7000, 6800, 7500, 8200, 7900, 8500, 8100, 7900, 7800, 8000, 8300]

df = pd.DataFrame(data)

plt.figure(figsize=(10,6))
plt.plot(df['Month'], df['Product_A_Sales'], label='Product A')

plt.plot(df['Month'], df['Product_B_Sales'], label='Product B')

plt.plot(df['Month'], df['Product_C_Sales'], label='Product C')

plt.title('Sales A, B, and C over the Months')

plt.xlabel('Month')

plt.ylabel('Sales')

plt.legend()

plt.show()

3 - . Bar Plot:

- Create a bar plot to compare the monthly sales of all three products.

- Ensure the plot has a title, labeled axes, and a legend.

ANS 3-

import pandas as pd

import matplotlib.pyplot as plt

data = {

'Month': ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October',
'November', 'December'],
 'Product_A_Sales': [5000, 6000, 7000, 8000, 7500, 8200, 7800, 8400, 8200, 8600, 8800, 9000],

'Product_B_Sales': [7000, 6500, 7200, 6800, 7000, 7300, 7100, 7600, 7200, 7300, 7400, 7500],

'Product_C_Sales': [8000, 7000, 6800, 7500, 8200, 7900, 8500, 8100, 7900, 7800, 8000, 8300]

df = pd.DataFrame(data)

plt.figure(figsize=(10,6))

plt.bar(df['Month'], df['Product_A_Sales'], label='Product A')

plt.bar(df['Month'], df['Product_B_Sales'], bottom=df['Product_A_Sales'], label='Product B')

plt.bar(df['Month'], df['Product_C_Sales'], bottom=df['Product_A_Sales'] + df['Product_B_Sales'],

label='Product C')

plt.title('Monthly Sales of Product A, B, and C')

plt.xlabel('Month')

plt.ylabel('Sales')

plt.legend()

plt.show()
Q4 - . Pie Chart - Create a pie chart to show the proportion of total annual sales contributed by
each product.

- Ensure the plot has a title and data labels.

ANS 4 –

import pandas as pd

import matplotlib.pyplot as plt

data = {

'Month': ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October',
'November', 'December'],

'Product_A_Sales': [5000, 6000, 7000, 8000, 7500, 8200, 7800, 8400, 8200, 8600, 8800, 9000],

'Product_B_Sales': [7000, 6500, 7200, 6800, 7000, 7300, 7100, 7600, 7200, 7300, 7400, 7500],

'Product_C_Sales': [8000, 7000, 6800, 7500, 8200, 7900, 8500, 8100, 7900, 7800, 8000, 8300]

df = pd.DataFrame(data)

df['Total_Sales'] = df[['Product_A_Sales', 'Product_B_Sales', 'Product_C_Sales']].sum(axis=1)

df['Average_Sales'] = df[['Product_A_Sales', 'Product_B_Sales', 'Product_C_Sales']].mean(axis=1)

total_product_a_sales = df['Product_A_Sales'].sum()

total_product_b_sales = df['Product_B_Sales'].sum()

total_product_c_sales = df['Product_C_Sales'].sum()

plt.figure(figsize=(6,6))

plt.pie([total_product_a_sales, total_product_b_sales, total_product_c_sales], labels=['Product A',

'Product B', 'Product C'], autopct='%1.1f%%')

plt.title(' Total Annual Sales by Product')

plt.axis('equal')

plt.show()
 Part 2: Advanced Data Visualization

Q1- Scatter Plot:

- Create a scatter plot to analyze the relationship between `Product_A_Sales` and

`Product_B_Sales`.

- Ensure the plot has a title, labeled axes, and a trendline

ANS-1

import pandas as pd

import matplotlib.pyplot as plt

import numpy as np

data = {

'Product_A_Sales': [5000, 6000, 7000, 8000, 7500, 8200, 7800, 8400, 8200, 8600, 8800, 9000],

'Product_B_Sales': [7000, 6500, 7200, 6800, 7000, 7300, 7100, 7600, 7200, 7300, 7400, 7500]

df = pd.DataFrame(data)

plt.figure(figsize=(8,6))

plt.scatter(df['Product_A_Sales'], df['Product_B_Sales'])
plt.title('Relationship between Product A Sales and Product B Sales')

plt.xlabel('Product A Sales')

plt.ylabel('Product B Sales')

z = np.polyfit(df['Product_A_Sales'], df['Product_B_Sales'], 1)

p = np.poly1d(z)

plt.plot(df['Product_A_Sales'],p(df['Product_A_Sales']),"r--")

plt.show()

Q 2- . Histogram:

- Create a histogram to show the distribution of `Total_Sales` across the months.

- Ensure the plot has a title and labeled axes

ANS 2

import pandas as pd

import matplotlib.pyplot as plt

data = {
 'Month': ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October',
'November', 'December'],

'Product_A_Sales': [5000, 6000, 7000, 8000, 7500, 8200, 7800, 8400, 8200, 8600, 8800, 9000],

'Product_B_Sales': [7000, 6500, 7200, 6800, 7000, 7300, 7100, 7600, 7200, 7300, 7400, 7500],

'Product_C_Sales': [8000, 7000, 6800, 7500, 8200, 7900, 8500, 8100, 7900, 7800, 8000, 8300]

df = pd.DataFrame(data)

df['Total_Sales'] = df['Product_A_Sales'] + df['Product_B_Sales'] + df['Product_C_Sales']

plt.figure(figsize=(8,6))

plt.hist(df['Total_Sales'], bins=10, edgecolor='black')

plt.title('Distribution Total Sales Across Months')

plt.xlabel('Total Sales')

plt.ylabel('Frequency')

plt.show()
Q 3- . Box Plot:

- Create a box plot to visualize the distribution of sales for Product A, Product B, and Product C.

- Ensure the plot has a title and labeled axes

ANS 3-

import pandas as pd

import matplotlib.pyplot as plt

data = {

'Month': ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October',
'November', 'December'],

'Product_A_Sales': [5000, 6000, 7000, 8000, 7500, 8200, 7800, 8400, 8200, 8600, 8800, 9000],

'Product_B_Sales': [7000, 6500, 7200, 6800, 7000, 7300, 7100, 7600, 7200, 7300, 7400, 7500],

'Product_C_Sales': [8000, 7000, 6800, 7500, 8200, 7900, 8500, 8100, 7900, 7800, 8000, 8300]

df = pd.DataFrame(data)
plt.figure(figsize=(8,6))

plt.boxplot([df['Product_A_Sales'], df['Product_B_Sales'], df['Product_C_Sales']], vert=True,

patch_artist=True)

plt.title('Distribution of Sales for Product A, Product B, and Product C')

plt.xlabel('Product')

plt.ylabel('Sales')

plt.xticks([1, 2, 3], ['Product A', 'Product B', 'Product C'])

plt.show()

Q 4 -. Heatmap:

- Create a heatmap to show the correlation between the sales of Product A, Product B, and
Product C.

- Ensure the plot has a title and a color bar

ANS 4-

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

import numpy as np

data = {

'Month': ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October',
'November', 'December'],

'Product_A_Sales': [5000, 6000, 7000, 8000, 7500, 8200, 7800, 8400, 8200, 8600, 8800, 9000],

'Product_B_Sales': [7000, 6500, 7200, 6800, 7000, 7300, 7100, 7600, 7200, 7300, 7400, 7500],

'Product_C_Sales': [8000, 7000, 6800, 7500, 8200, 7900, 8500, 8100, 7900, 7800, 8000, 8300]

df = pd.DataFrame(data)

corr_matrix = df[['Product_A_Sales', 'Product_B_Sales', 'Product_C_Sales']].corr()

plt.figure(figsize=(8,6))

sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', vmin=-1, vmax=1, square=True)

plt.title('Correlation Between Product A, Product B, and Product C Sales')

plt.show()
 Part 3: Customization and Presentation

Q1-. Plot Customization:

- Customize the plots with appropriate colors, markers, and styles to make them visually
appealing and informative.

- Use annotations where necessary to highlight key data points

ANS 1-

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

import numpy as np

data = {

'Month': ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October',
'November', 'December'],

'Product_A_Sales': [5000, 6000, 7000, 8000, 7500, 8200, 7800, 8400, 8200, 8600, 8800, 9000],

'Product_B_Sales': [7000, 6500, 7200, 6800, 7000, 7300, 7100, 7600, 7200, 7300, 7400, 7500],

'Product_C_Sales': [8000, 7000, 6800, 7500, 8200, 7900, 8500, 8100, 7900, 7800, 8000, 8300]

df = pd.DataFrame(data)

plt.figure(figsize=(10,6))

plt.plot(df['Month'], df['Product_A_Sales'], marker='o', linestyle='-', color='black', label='Product A')

plt.plot(df['Month'], df['Product_B_Sales'], marker='s', linestyle='--', color='red', label='Product B')

plt.plot(df['Month'], df['Product_C_Sales'], marker='D', linestyle='-.', color='green', label='Product C')

plt.title('Monthly Sales of Product A, Product B, and Product C')

plt.xlabel('Month')

plt.ylabel('Sales')

plt.legend()

plt.grid(True)
max_sales_a = df['Product_A_Sales'].max()

max_sales_b = df['Product_B_Sales'].max()

max_sales_c = df['Product_C_Sales'].max()

plt.annotate(f'Max Sales: {max_sales_a}', xy=(df['Month'][df['Product_A_Sales'].idxmax()],

max_sales_a), xytext=(10,10), textcoords='offset points', ha='center')

plt.annotate(f'Max Sales: {max_sales_b}', xy=(df['Month'][df['Product_B_Sales'].idxmax()],

max_sales_b), xytext=(10,10), textcoords='offset points', ha='center')

plt.annotate(f'Max Sales: {max_sales_c}', xy=(df['Month'][df['Product_C_Sales'].idxmax()],

max_sales_c), xytext=(10,10), textcoords='offset points', ha='center')

plt.show()

plt.figure(figsize=(8,6))

plt.boxplot([df['Product_A_Sales'], df['Product_B_Sales'], df['Product_C_Sales']], vert=True,

patch_artist=True)

plt.title('Distribution of Sales for Product A, Product B, and Product C')

plt.xlabel('Product')

plt.ylabel('Sales')

plt.xticks([1, 2, 3], ['Product A', 'Product B', 'Product C'])

plt.show()

corr_matrix = df[['Product_A_Sales', 'Product_B_Sales', 'Product_C_Sales']].corr()

plt.figure(figsize=(8,6))

sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', vmin=-1, vmax=1, square=True)

plt.title('Correlation Between Product A, Product B, and Product C Sales')

plt.show()
Q 2- . Subplots:

- Create a single figure with multiple subplots to present the data in a cohesive manner.

- Ensure the figure has a main title and each subplot is clearly labelled

ANS 2-

import matplotlib.pyplot as plt

import pandas as pd

data = {

'Month': ['January', 'February', 'March', 'April', 'May', 'June', 'July', 'August', 'September', 'October',
'November', 'December'],
 'Product_A_Sales': [5000, 6000, 7000, 8000, 7500, 8200, 7800, 8400, 8200, 8600, 8800, 9000],

'Product_B_Sales': [7000, 6500, 7200, 6800, 7000, 7300, 7100, 7600, 7200, 7300, 7400, 7500],

'Product_C_Sales': [8000, 7000, 6800, 7500, 8200, 7900, 8500, 8100, 7900, 7800, 8000, 8300]

df = pd.DataFrame(data)

df['Total_Sales'] = df[['Product_A_Sales', 'Product_B_Sales', 'Product_C_Sales']].sum(axis=1)

df['Average_Sales'] = df[['Product_A_Sales', 'Product_B_Sales', 'Product_C_Sales']].mean(axis=1)

fig, axs = plt.subplots(3, 1, figsize=(10, 12))

axs[0].plot(df['Month'], df['Product_A_Sales'], label='Product A')

axs[0].plot(df['Month'], df['Product_B_Sales'], label='Product B')

axs[0].plot(df['Month'], df['Product_C_Sales'], label='Product C')

axs[0].set_title('Monthly Sales by Product')

axs[0].set_xlabel('Month')

axs[0].set_ylabel('Sales')

axs[0].legend()

axs[1].plot(df['Month'], df['Total_Sales'])

axs[1].set_title('Total Monthly Sales')

axs[1].set_xlabel('Month')

axs[1].set_ylabel('Total Sales')

axs[2].plot(df['Month'], df['Average_Sales'])

axs[2].set_title('Average Monthly Sales')

axs[2].set_xlabel('Month')

axs[2].set_ylabel('Average Sales')

fig.suptitle('Monthly Sales Analysis')

fig.tight_layout(rect=[0, 0.03, 1, 0.95]

plt.show()