EDA Report Technology Trends .ipynb

Kernel: Python 3 (ipykernel)

import pandas as pd
import numpy as np

# Generate data
np.random.seed(0)
years = np.random.randint(2010, 2023, 3000)
technologies = ['Python', 'JavaScript', 'Java', 'C#', 'C++', 'Ruby', 'Swift', 'Go', 'Rust', 'Kotlin']
categories = ['Programming Language', 'Framework', 'Tool', 'Library', 'Platform', 'Database', 'Language', 'IDE', 'Framework', 'Tool']
popularity_index = np.random.uniform(0, 100, 3000)
growth_rate = np.random.uniform(-10, 10, 3000)
usage = np.random.randint(1000, 1000000, 3000)
market_share = np.random.uniform(0, 50, 3000)
regions = ['North America', 'Europe', 'Asia', 'South America', 'Africa']
industries = ['IT', 'Finance', 'Healthcare', 'Manufacturing', 'Education']
comments = ['None'] * 3000

# Create DataFrame
df = pd.DataFrame({
    'Year': years,
    'Technology': np.random.choice(technologies, 3000),
    'Category': np.random.choice(categories, 3000),
    'Popularity_Index': popularity_index,
    'Growth_Rate': growth_rate,
    'Usage': usage,
    'Market_Share': market_share,
    'Region': np.random.choice(regions, 3000),
    'Industry': np.random.choice(industries, 3000),
    'Comments': comments
})

# Save DataFrame to CSV
df.to_csv('technology_trends.csv', index=False)

df = pd.read_csv('technology_trends.csv')
df

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

# Load the dataset
df = pd.read_csv('technology_trends.csv')

# Display basic information about the dataset
print("Dataset Information:")
print(df.info())

# Summary statistics
print("\nSummary Statistics:")
print(df.describe())

# Check for missing values
print("\nMissing Values:")
print(df.isnull().sum())

# Visualization 1: Popularity Index Distribution (Histogram)
plt.figure(figsize=(10, 6))
sns.histplot(df['Popularity_Index'], bins=20, kde=True, color='skyblue')
plt.title('Distribution of Popularity Index')
plt.xlabel('Popularity Index')
plt.ylabel('Frequency')
plt.show()

# Visualization 2: Growth Rate by Category (Box Plot)
plt.figure(figsize=(10, 6))
sns.boxplot(x='Category', y='Growth_Rate', data=df, palette='Set2')
plt.title('Growth Rate by Category')
plt.xlabel('Category')
plt.ylabel('Growth Rate')
plt.xticks(rotation=45)
plt.show()

# Visualization 3: Market Share by Region (Bar Plot)
plt.figure(figsize=(10, 6))
sns.barplot(x='Region', y='Market_Share', data=df, estimator=np.mean, ci=None, palette='viridis')
plt.title('Average Market Share by Region')
plt.xlabel('Region')
plt.ylabel('Average Market Share')
plt.xticks(rotation=45)
plt.show()



# Visualization 5: Popularity Index vs. Growth Rate (Scatter Plot)
plt.figure(figsize=(10, 6))
sns.scatterplot(x='Popularity_Index', y='Growth_Rate', data=df, hue='Category', palette='Dark2')
plt.title('Popularity Index vs. Growth Rate')
plt.xlabel('Popularity Index')
plt.ylabel('Growth Rate')
plt.legend(title='Category')
plt.show()

# Visualization 6: Market Share by Technology (Pie Chart)
plt.figure(figsize=(10, 6))
market_share_by_tech = df.groupby('Technology')['Market_Share'].sum().sort_values(ascending=False)
plt.pie(market_share_by_tech, labels=market_share_by_tech.index, autopct='%1.1f%%', startangle=140)
plt.title('Market Share by Technology')
plt.axis('equal')
plt.show()

# Visualization 7: Usage Distribution by Year (Line Plot)
plt.figure(figsize=(10, 6))
sns.lineplot(x='Year', y='Usage', data=df, estimator=np.mean, ci=None, marker='o')
plt.title('Usage Distribution by Year')
plt.xlabel('Year')
plt.ylabel('Average Usage')
plt.xticks(rotation=45)
plt.show()

# Visualization 8: Popularity Index Distribution by Category (Histograms)
plt.figure(figsize=(12, 8))
sns.histplot(data=df, x='Popularity_Index', hue='Category', bins=20, multiple='stack', palette='Set2')
plt.title('Popularity Index Distribution by Category')
plt.xlabel('Popularity Index')
plt.ylabel('Frequency')
plt.show()

# Visualization 9: Market Share by Region and Industry (Heatmap)
plt.figure(figsize=(10, 6))
market_share_pivot = df.pivot_table(index='Region', columns='Industry', values='Market_Share', aggfunc=np.mean)
sns.heatmap(market_share_pivot, cmap='coolwarm', annot=True, fmt=".1f")
plt.title('Market Share by Region and Industry')
plt.xlabel('Industry')
plt.ylabel('Region')
plt.show()

# Visualization 10: Growth Rate Trend by Technology (Area Plot)
plt.figure(figsize=(10, 6))
growth_rate_trend = df.groupby('Year')['Growth_Rate'].mean()
sns.lineplot(x=growth_rate_trend.index, y=growth_rate_trend.values, marker='o', color='orange')
plt.title('Average Growth Rate Trend')
plt.xlabel('Year')
plt.ylabel('Average Growth Rate')
plt.xticks(rotation=45)
plt.grid(True)
plt.show()

Dataset Information:
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3000 entries, 0 to 2999
Data columns (total 10 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   Year              3000 non-null   int64  
 1   Technology        3000 non-null   object 
 2   Category          3000 non-null   object 
 3   Popularity_Index  3000 non-null   float64
 4   Growth_Rate       3000 non-null   float64
 5   Usage             3000 non-null   int64  
 6   Market_Share      3000 non-null   float64
 7   Region            3000 non-null   object 
 8   Industry          3000 non-null   object 
 9   Comments          3000 non-null   object 
dtypes: float64(3), int64(2), object(5)
memory usage: 234.5+ KB
None

Summary Statistics:
              Year  Popularity_Index  Growth_Rate          Usage  Market_Share
count  3000.000000       3000.000000  3000.000000    3000.000000   3000.000000
mean   2015.993333         50.300724     0.130376  495705.509667     25.078948
std       3.748774         28.952742     5.727954  285066.826091     14.522436
min    2010.000000          0.018671    -9.999599    1597.000000      0.001629
25%    2013.000000         25.270949    -4.734733  255163.750000     12.507861
50%    2016.000000         50.648571     0.174553  494828.000000     24.749080
75%    2019.000000         75.997921     5.119626  741175.000000     37.873498
max    2022.000000         99.989729     9.996769  999955.000000     49.998547

Missing Values:
Year                0
Technology          0
Category            0
Popularity_Index    0
Growth_Rate         0
Usage               0
Market_Share        0
Region              0
Industry            0
Comments            0
dtype: int64