Predictions download formats: Text token classification

Overview

When you download predictions in H2O Hydrogen Torch, which comes in a zip file, the format and content of the file first depends on the problem type of the predictions, and then it depends on how you generate them. On the point of "how you generate them," there are two scenarios.

• Scenario 1: Predictions from a completed experiment

  Predictions downloaded from a completed experiment on the View experiments card are packaged in a zip file. This zip file contains the following files:

  1. validation_predictions.csv: This is a structured dataframe in CSV format, presenting the final predictions for the provided validation dataframe.

  2. validation_raw_predictions.pkl: This is a Pickle file, which is essentially a pickled Python dictionary. It contains raw predictions for the provided validation dataframe.

     If the experiment included a test dataframe, H2O Hydrogen Torch also includes two additional files in the same zip file:

  3. test_predictions.csv: This is another structured dataframe in CSV format, displaying the final predictions for the provided test dataframe.

  4. test_raw_predictions.pkl: Similar to the validation set, this is a Pickle file with raw predictions for the provided test dataframe.

• Scenario 2: Predictions generated by scoring on new data

  Predictions generated by scoring on new data through the H2O Hydrogen Torch UI (on the Predict data card) are downloaded in a zip file. This zip file includes the following files:

  1. test_predictions.csv: This is a structured dataframe in CSV format, showing the final predictions for the provided test dataframe.
  2. test_raw_predictions.pkl: This is a Pickle file, a pickled Python dictionary containing raw predictions for the provided test dataframe.

Formats

`.pkl` file keys

The Pickle file, contains the following keys:

• probabilities
  • A list of 2-dimensional NumPy arrays that contains word-level probabilities for each token, where the length of the list is N (number_of_observations). The shape of each array in the list is as follows: text_length x number_of_classes, where text_length is the number of words in the input text
• predictions
  • A 1-dimensional NumPy array that contains predictions in the form of a list of predicted classes for each input word found in the input text
• labels
  • A 1-dimensional NumPy array that contains label names
• [text_column]
  • A 1-dimensional NumPy array that contains input texts. The name of the key is [text_column] where text_column refers to the name of the text column in the train dataframe

`.csv` file columns

The csv file contains the following columns:

• All the N columns found in the train dataframe
• A column named pred_{label_column_name} containing predictions for the {label_column_name} column in a form of a string space-separated by predicted classes for each input word
  Note

  You can define the label_column_name under the Dataset settings section when building a text token classification experiment.

Note

• The i-th sample of each output's dictionary item matches the i-th row of the dataframe.
• To learn how to open the csv and Pickle files, see Open CSV and Pickle files with Python.

Open CSV and Pickle files with Python

Using Python, a csv or Pickle file containing predictions can be open as follows:

import pickle
import pandas as pd

df = pd.read_csv('text_classification/validation_predictions.csv')

with open('text_classification/validation_raw_predictions.pkl', 'rb') as f:
    out = pickle.load(f)

print(out.keys())

dict_keys(['predictions', 'comment_text', 'labels'])

print(df.head(1))

id	comment_text	label_toxic	label_severe_toxic	label_obscene	label_threat	label_insult	label_identity_hate	fold	pred_label_toxic	pred_label_severe_toxic	pred_label_obscene	pred_label_threat	pred_label_insult	pred_label_identity_hate
000103f0d9cfb60f	D'aww! He matches this background colour I'm s...	0	0	0	0	0	0	0	0.00041	0.000168	0.000328	0.000142	0.000247	0.000155

---

Feedback

• Submit and view feedback for this page
• Send feedback about H2O Hydrogen Torch to cloud-feedback@h2o.ai