ChatGPT: your mind will explode!

Turribeach
Turribeach Dataiku DSS Core Designer, Neuron, Dataiku DSS Adv Designer, Registered, Neuron 2023 Posts: 2,024 Neuron

If you haven't heard of ChatGPT, get ready to have your mind explode! This is chatbot that has been trained to respond to questions iusing natural language. The most interesting thing is that it understands code and APIs and can suggest code to you with an explanation. See sample below:

Screenshot 2022-12-13 at 2.09.20 pm.png

Answers

  • tgb417
    tgb417 Dataiku DSS Core Designer, Dataiku DSS & SQL, Dataiku DSS ML Practitioner, Dataiku DSS Core Concepts, Neuron 2020, Neuron, Registered, Dataiku Frontrunner Awards 2021 Finalist, Neuron 2021, Neuron 2022, Frontrunner 2022 Finalist, Frontrunner 2022 Winner, Dataiku Frontrunner Awards 2021 Participant, Frontrunner 2022 Participant, Neuron 2023 Posts: 1,598 Neuron
    edited July 17

    Here is a little more code written for Dataiku by ChatGPT

    # Import the necessary packages
    import dataiku
    import datetime
    import os
    import pandas as pd
    import zlib

    # Get the project variables as a dictionary
    project_variables = dataiku.get_custom_variables()

    # Access the value of the file path project variable
    base_path = project_variables["base_path"]

    # Expand the '~' character in the file path to the full path to your home directory
    base_path = os.path.expanduser(base_path)

    # List the names of all the files and directories in the directory
    file_names = os.listdir(base_path)

    # Create an empty list to store the full file paths, last modified dates, and calculated CRC values
    file_crcs = []

    # Iterate over the list of file names
    for file_name in file_names:
    # Create the full file path
    file_path = os.path.join(base_path, file_name)

    # Check if the path is a file
    if not os.path.isdir(file_path):
    # Get the last modified timestamp of the file
    last_modified_timestamp = os.path.getmtime(file_path)

    # Convert the last modified timestamp to a human-readable date and time
    last_modified_date = datetime.datetime.fromtimestamp(last_modified_timestamp)

    # Open the file in binary mode
    with open(file_path, "rb") as file:
    # Read the file in binary mode and calculate the CRC value
    crc = zlib.crc32(file.read())

    # Store the full file path, last modified date, and calculated CRC value in the list
    file_crcs.append([file_path, last_modified_date, crc])

    # Create a Pandas DataFrame from the list of file paths, last modified dates, and CRC values
    df = pd.DataFrame(file_crcs, columns=["File Path", "Last Modified Date", "CRC Value"])

    # Get the Dataiku dataset object for the 'File_CRC_Values' dataset
    dataset = dataiku.Dataset("File_CRC_Values")

    # Write the Pandas DataFrame to the Dataiku dataset, using the schema of the dataset
    dataset.write_with_schema(df)
  • Turribeach
    Turribeach Dataiku DSS Core Designer, Neuron, Dataiku DSS Adv Designer, Registered, Neuron 2023 Posts: 2,024 Neuron

    It's really amazing it can be trained on so many languages. Enjoy it while it lasts! I can't see it being free for too long, their infrastructure costs must be huge (they claim it cost them 10x the cost of a Google search query). So I think this will become a paid service. Having said that I wouldn't mind paying something for a service like this.

Setup Info
    Tags
      Help me…