Learning How to Code

Schema

What Is Python?
Understanding Python as a Language
Why Generative AI Is Helpful for Coding Purposes
Writing Good Prompts
Get Familiar with the Environments – Google Colab

Slides

Another Coding Environments

Visual Studio Code Tutorial

Resources

Activity

Python Scripts

Open CSV

import pandas as pd

file_path = "/content/knoedler.csv"

try:
    df = pd.read_csv(file_path, low_memory=False)
    print("✓ CSV file loaded successfully!\n")
except FileNotFoundError:
    print(f"Error: File '{file_path}' not found.")
    print("Download from: https://github.com/thegetty/provenance-index-csv/tree/main/knoedler")
    exit()

Read column names

print("=" * 60)
print("COLUMN NAMES")
print("=" * 60)
columns = df.columns.tolist()
for i, col in enumerate(columns, 1):
    print(f"  {i}. {col}")
print(f"\nTotal columns: {len(columns)}\n")

Check number of rows

print("=" * 60)
print("DATASET DIMENSIONS")
print("=" * 60)
num_rows = len(df)
num_cols = len(df.columns)
print(f"  Number of rows: {num_rows:,}")
print(f"  Number of columns: {num_cols}")
print(f"  Total cells: {num_rows * num_cols:,}\n")

Unique values in a column

print("=" * 60)
print("UNIQUE VALUES ANALYSIS")
print("=" * 60)

# Function to get unique values for any column
def get_unique_values(dataframe, column_name):
    """Return unique values and count for a specified column."""
    if column_name not in dataframe.columns:
        print(f"Column '{column_name}' not found in dataset.")
        return None

    unique_vals = dataframe[column_name].dropna().unique()
    unique_count = len(unique_vals)

    print(f"\nColumn: '{column_name}'")
    print(f"  Unique values: {unique_count:,}")
    print(f"  Missing values: {dataframe[column_name].isna().sum():,}")

    # Show sample of unique values (first 10)
    if unique_count > 0:
        print(f"  Sample values (up to 10):")
        for val in list(unique_vals)[:10]:
            print(f"    - {val}")

    return unique_vals

# Analyze a few columns (adjust column names based on actual data)
# Common columns in Knoedler data: 'artist_name', 'title', 'genre', 'sale_date'
sample_columns = columns[:3]  # Analyze first 3 columns as example

for col in sample_columns:
    get_unique_values(df, col)

Save a CSV (filtered or processed data)

print("\n" + "=" * 60)
print("SAVING PROCESSED DATA")
print("=" * 60)

# Example: Save a summary of missing data per column
missing_data = pd.DataFrame({
    'column': df.columns,
    'missing_count': df.isnull().sum().values,
    'missing_percent': (df.isnull().sum().values / len(df) * 100).round(2),
    'unique_values': [df[col].nunique() for col in df.columns]
})

output_file = "provenance_data_summary.csv"
missing_data.to_csv(output_file, index=False)
print(f"✓ Summary saved to '{output_file}'\n")

# Optional: Save filtered subset
# Example: Save rows where a specific column has missing data
# df_with_gaps = df[df['artist_name'].isna()]
# df_with_gaps.to_csv("records_missing_artist.csv", index=False)

print("=" * 60)
print("SCRIPT COMPLETE")
print("=" * 60)

© 2025 Coding Provenance Workshop — Licensed under a Creative Commons Attribution 4.0 International License.
Reuse is encouraged — we happily promote changes of custody. Just be sure to write a good provenance record and cite this workshop.