Day1 Visualization using Seaborne.ipynb

Kernel: Python 3 (ipykernel)

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# Generating sample data
np.random.seed(0)
data = {
    'Technology': np.random.choice(['Python', 'Java', 'JavaScript', 'C++', 'Ruby'], 3000),
    'Usage': np.random.randint(1, 11, 3000),
    'Popularity': np.random.randint(1, 101, 3000),
    'Cost': np.random.uniform(100, 1000, 3000),
    'Innovation': np.random.randint(1, 6, 3000)
}
df = pd.DataFrame(data)

# Calculate average usage of each technology
tech_usage_mean = df.groupby('Technology')['Usage'].mean().reset_index()

import seaborn as sns

# Calculate average usage of each technology
tech_usage_mean = df.groupby('Technology')['Usage'].mean().reset_index()

# Histogram
plt.figure(figsize=(8, 6))
sns.histplot(df['Usage'], bins=20, color='skyblue', edgecolor='black')
plt.title('Usage Distribution')
plt.xlabel('Usage')
plt.ylabel('Frequency')
plt.grid(True)
plt.show()

# Scatter plot
plt.figure(figsize=(8, 6))
sns.scatterplot(x='Popularity', y='Cost', data=df, color='orange', alpha=0.5)
plt.title('Popularity vs Cost')
plt.xlabel('Popularity')
plt.ylabel('Cost')
plt.grid(True)
plt.show()

# Bar plot
plt.figure(figsize=(10, 6))
sns.countplot(x='Technology', data=df, palette='Greens')
plt.title('Technology Distribution')
plt.xlabel('Technology')
plt.ylabel('Count')
plt.xticks(rotation=45)
plt.grid(axis='y')
plt.show()

# Box plot
plt.figure(figsize=(8, 6))
sns.boxplot(x=df['Innovation'], orient='h')
plt.title('Innovation Distribution')
plt.xlabel('Innovation')
plt.grid(True)
plt.show()

# Line chart
plt.figure(figsize=(10, 6))
sns.lineplot(x='Technology', y='Usage', data=tech_usage_mean, marker='o')
plt.title('Average Usage of Technologies')
plt.xlabel('Technology')
plt.ylabel('Average Usage')
plt.xticks(rotation=45)
plt.grid(True)
plt.show()

# Scatter plot with regression line
plt.figure(figsize=(8, 6))
sns.regplot(x='Popularity', y='Cost', data=df, color='purple', scatter_kws={'alpha':0.5})
plt.title('Popularity vs Cost with Regression Line')
plt.xlabel('Popularity')
plt.ylabel('Cost')
plt.grid(True)
plt.show()