Data Analysis

Data Analysis Skill

This skill enables deep data exploration, cleaning, aggregation, and visualization using Python's standard data science stack.

Core Capabilities

1. Read Data: Load data from CSV (.csv), Excel (.xlsx), JSON (.json), or Parquet files.
2. Clean & Transform: Filter rows, handle missing values, reshape data (melt/pivot).
3. Aggregate: Group by columns, calculate sums/means/counts or custom metrics.
4. Visualize: Generate static plots (bar, line, scatter, histogram, boxplot, heatmap) using Matplotlib and Seaborn.

Dependencies

• pandas (pip install pandas openpyxl)
• matplotlib (pip install matplotlib)
• seaborn (pip install seaborn)

Workflow Examples

1. Basic Statistical Summary

import pandas as pd

# Load data
df = pd.read_csv('data.csv')

# Inspect basics
print(df.head())
print(df.info())
print(df.describe())

# Check for missing values
print(df.isnull().sum())

2. Visualization: Correlation Heatmap

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

df = pd.read_csv('dataset.csv')
corr = df.corr()

plt.figure(figsize=(10, 8))
sns.heatmap(corr, annot=True, cmap='coolwarm')
plt.title('Correlation Matrix')
plt.savefig('correlation_heatmap.png')

3. Aggregation and Bar Chart

import pandas as pd
import matplotlib.pyplot as plt

df = pd.read_excel('sales_data.xlsx')

# Group by Category and Sum Sales
category_sales = df.groupby('Category')['Sales'].sum().sort_values(ascending=False)

plt.figure(figsize=(12, 6))
category_sales.plot(kind='bar', color='skyblue')
plt.title('Total Sales by Category')
plt.xlabel('Category')
plt.ylabel('Sales ($)')
plt.tight_layout()
plt.savefig('sales_by_category.png')

Best Practices

• Avoid large loops: Use vectorized Pandas operations.
• Handle Errors: Wrap file reading in try-except blocks.
• Visual Clarity: Always label axes and titles in plots.
• File Formats: Specify engine='openpyxl' for .xlsx files if needed.