INNER CODE UNIT · Python
extract_data_from_csv
balapriyac/data-science-tutorials · build-with-python/etl-pipeline/main.py:25
def extract_data_from_csv(csv_file_path):
"""Extract: Load data from CSV file (simulating download from external source)"""
try:
print(f"Extracting data from {csv_file_path}...")
df = pd.read_csv(csv_file_path)
print(f"Successfully extracted {len(df)} records")
return df
except FileNotFoundError:
print(f"Error: {csv_file_path} not found. Creating sample data...")
csv_file = create_sample_csv_data()
return pd.read_csv(csv_file)
def transform_data(df):
"""Transform: Clean and enrich the data"""
print("Transforming data...")
# Start with a copy to avoid modifying original
df_clean = df.copy()