dataengine

import dataengine as de import os import pandas as pd # Used for creating dummy data file # Create a dummy CSV file for the example dummy_csv_content = "id,name,value\n1,Alice,100\n2,Bob,200\n3,Charlie,150" temp_csv_file = "temp_quickstart.csv" with open(temp_csv_file, "w") as f: f.write(dummy_csv_content) try: # 1. Initialize a session (PandasSession is simplest for local execution) # For Spark, you would use: session = de.SparkSession() (requires pyspark) session = de.PandasSession() print(f"Initialized session type: {session.__class__.__name__}") # 2. Create a DataFrame directly from Python data data = {'item': ['apple', 'banana', 'orange'], 'price': [1.0, 0.5, 0.75]} df_from_dict = de.PandasDataFrame(data=data) print("\nDataFrame created from dict:") print(df_from_dict.to_pandas()) # 3. Read data from the temporary CSV file csv_reader = de.CSV(session) df_from_csv = csv_reader.read(temp_csv_file) print("\nDataFrame read from temporary CSV file:") print(df_from_csv.to_pandas()) # 4. Perform a simple transformation (e.g., filter) filtered_df = df_from_csv.filter(df_from_csv['value'] > 100) print("\nFiltered DataFrame (value > 100):") print(filtered_df.to_pandas()) # 5. Example of writing (conceptual - actual write requires specific setup) # For instance: filtered_df.write.parquet("output.parquet") except Exception as e: print(f"An error occurred during quickstart: {e}") finally: # Clean up the dummy file if os.path.exists(temp_csv_file): os.remove(temp_csv_file) print("\nQuickstart complete. Explore de.SparkSession, de.PolarsDataFrame, de.Parquet etc. for more advanced usage.")