Introduction to Pandas

import pandas as pd
import numpy as np

# Pandas provides two core data structures:
# 1. Series  — 1D labeled array
# 2. DataFrame — 2D labeled table (columns of different types)

# Key Pandas capabilities:
print("""
Pandas can:
✅ Read CSV, Excel, JSON, SQL, Parquet, HDF5
✅ Clean messy, incomplete data
✅ Filter, select, transform data
✅ Group and aggregate (like SQL GROUP BY)
✅ Merge datasets (like SQL JOIN)
✅ Handle dates and time series
✅ Visualize data
✅ Export to multiple formats
""")

# Series: 1D array with a labeled index
s = pd.Series([10, 20, 30, 40, 50])
print(s)
# 0    10
# 1    20
# dtype: int64

# Custom index
s_named = pd.Series(
    [85, 92, 78, 96],
    index=['Math', 'Science', 'English', 'History'],
    name='Alice_Scores'
)
print(s_named)
print(f"\nMath score: {s_named['Math']}")      # 85
print(f"Mean score: {s_named.mean():.1f}")    # 87.75

# Series from dict
city_pop = pd.Series({'NYC': 8.3, 'LA': 3.9, 'Chicago': 2.7, 'Houston': 2.3})
print(city_pop.sort_values(ascending=False))

# DataFrame: 2D table — the primary Pandas structure
data = {
    'Employee': ['Alice', 'Bob', 'Carol', 'David', 'Eve'],
    'Department': ['Engineering', 'Marketing', 'Engineering', 'Sales', 'HR'],
    'Salary': [85000, 62000, 91000, 55000, 58000],
    'Experience': [5, 3, 8, 2, 4],
    'Rating': [4.5, 3.8, 4.9, 3.5, 4.1]
}

df = pd.DataFrame(data)
print(df)
print("\nShape:", df.shape)          # (5, 5)
print("Columns:", list(df.columns))
print("Index:", list(df.index))

# DataFrame attributes
print(df.dtypes)          # Data types per column
print(df.info())          # Overview: shape, dtypes, memory
print(df.describe())      # Statistical summary of numeric cols

# Column access
print(df['Salary'])                    # Single column → Series
print(df[['Employee', 'Salary']])      # Multiple columns → DataFrame

# Row access
print(df.head(3))                      # First 3 rows
print(df.tail(2))                      # Last 2 rows
print(df.iloc[0])                      # First row by position
print(df.loc[2])                       # Row with index label 2

# Quick statistics
print(df['Salary'].mean())             # 70200
print(df['Salary'].max())              # 91000
print(df['Department'].value_counts()) # Counts per department

import pandas as pd

employees = pd.DataFrame({
    'Name': ['Alice','Bob','Carol','David','Eve','Frank','Grace','Henry'],
    'Dept': ['Eng','Mkt','Eng','Sales','HR','Eng','Mkt','Sales'],
    'Salary': [85000, 62000, 91000, 55000, 58000, 78000, 67000, 49000],
    'Experience': [5, 3, 8, 2, 4, 6, 4, 1],
    'Rating': [4.5, 3.8, 4.9, 3.5, 4.1, 4.3, 4.0, 3.2]
})

print("=" * 50)
print("EMPLOYEE ANALYSIS REPORT")
print("=" * 50)

# Basic info
print(f"\nTotal employees: {len(employees)}")
print(f"Departments: {employees['Dept'].unique()}")

# Salary analysis
print(f"\nSalary Statistics:")
print(f"  Average: ${employees['Salary'].mean():,.0f}")
print(f"  Highest: ${employees['Salary'].max():,} ({employees.loc[employees['Salary'].idxmax(), 'Name']})")
print(f"  Lowest:  ${employees['Salary'].min():,} ({employees.loc[employees['Salary'].idxmin(), 'Name']})")

# Department summary
print("\nDepartment Summary:")
dept_summary = employees.groupby('Dept').agg(
    Count=('Name', 'count'),
    Avg_Salary=('Salary', 'mean'),
    Avg_Rating=('Rating', 'mean')
).round(2)
print(dept_summary)

# Top performers
print("\nTop Performers (Rating ≥ 4.3):")
top = employees[employees['Rating'] >= 4.3][['Name', 'Dept', 'Salary', 'Rating']]
print(top.to_string(index=False))

# Salary vs experience correlation
correlation = employees['Salary'].corr(employees['Experience'])
print(f"\nSalary-Experience Correlation: {correlation:.3f}")