Load Data

load_data.py

def load_data(df, split=0.2):
    """
    Function From Spacy
    Prepare the training data as per Spacy format
    Parameters:
        df: training data in pandas dataframe
        split: float - Splitting dataframe to train and validation set. Defaults to 0.2
    Returns:
        tuples: train and validation text and labels
    """
    # Shuffle the data
    df_train = df_tolist(df)
    random.shuffle(df_train)
    texts, labels = zip(*df_train)
    # get the categories for each sentence
    cats = [{"POSITIVE": bool(y), "NEGATIVE": not bool(y)} for y in labels]
    # Splitting the training and evaluation data
    split = int(len(df_train) * split)
    return (texts[:split], cats[:split]), (texts[split:], cats[split:])