#Pandas Installation

# Verify Pandas installation
import pandas as pd
print(f"Pandas version: {pd.__version__}")

# Verify core functionality
df = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})
print(df)

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Pandas Environment Verification Script
"""

def check_pandas_installation():
    """Check Pandas and related library installation status"""
    
    print("=" * 50)
    print("Pandas Environment Check")
    print("=" * 50)
    
    # Check core libraries
    libraries = {
        'pandas': 'pd',
        'numpy': 'np',
        'matplotlib': 'plt',
        'seaborn': 'sns'
    }
    
    for lib_name, alias in libraries.items():
        try:
            lib = __import__(lib_name)
            version = getattr(lib, '__version__', 'Unknown version')
            print(f"✅ {lib_name:12} {version}")
        except ImportError:
            print(f"❌ {lib_name:12} Not installed")
    
    # Test basic functionality
    print("\n" + "=" * 50)
    print("Functionality Test")
    print("=" * 50)
    
    try:
        import pandas as pd
        import numpy as np
        
        # Create test data
        df = pd.DataFrame({
            'Name': ['Alice', 'Bob', 'Charlie'],
            'Age': [25, 30, 35],
            'City': ['Beijing', 'Shanghai', 'Guangzhou']
        })
        
        print("✅ DataFrame creation successful")
        print(df)
        
        # Basic statistics
        print(f"\n✅ Average age: {df['Age'].mean():.1f}")
        
        # Data filtering
        young = df[df['Age'] < 30]
        print(f"✅ Number of people under 30: {len(young)}")
        
        print("\n🎉 All tests passed! Pandas environment configured successfully!")
        
    except Exception as e:
        print(f"❌ Test failed: {e}")

if __name__ == "__main__":
    check_pandas_installation()

import pandas as pd
import numpy as np
import time

def performance_test():
    """Simple performance test"""
    
    print("Starting performance test...")
    
    # Create large dataset
    n = 1000000
    start_time = time.time()
    
    df = pd.DataFrame({
        'A': np.random.randn(n),
        'B': np.random.randn(n),
        'C': np.random.choice(['X', 'Y', 'Z'], n)
    })
    
    create_time = time.time() - start_time
    
    # Execute operations
    start_time = time.time()
    result = df.groupby('C')['A'].mean()
    operation_time = time.time() - start_time
    
    print(f"Time to create {n:,} rows: {create_time:.2f} seconds")
    print(f"Time for group aggregation: {operation_time:.2f} seconds")
    print(f"Memory usage: {df.memory_usage(deep=True).sum() / 1024**2:.1f} MB")

performance_test()

# Check Python path
import sys
print(sys.path)

# Check installation location
import pandas
print(pandas.__file__)

import pandas as pd

# View all configuration options
print(pd.describe_option())

# Common configurations
pd.set_option('display.max_rows', 100)        # Display rows
pd.set_option('display.max_columns', 20)      # Display columns
pd.set_option('display.width', 1000)          # Display width
pd.set_option('display.precision', 2)         # Decimal precision
pd.set_option('display.float_format', '{:.2f}'.format)  # Float format

# Reset configuration
pd.reset_option('all')

# Enable string inference
pd.set_option('future.infer_string', True)

# Enable Copy-on-Write
pd.set_option('mode.copy_on_write', True)

# Set computation engine
pd.set_option('compute.use_bottleneck', True)
pd.set_option('compute.use_numexpr', True)

# Recommended settings for Jupyter
%matplotlib inline
%config InlineBackend.figure_format = 'retina'

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

# Set font for CJK characters (resolve display issues)
plt.rcParams['font.sans-serif'] = ['SimHei', 'Arial Unicode MS']
plt.rcParams['axes.unicode_minus'] = False

# Pandas display configuration
pd.set_option('display.max_columns', None)
pd.set_option('display.width', None)
pd.set_option('display.max_colwidth', 100)