import string
import pandas as pd
from sklearn.model_selection import train_test_split
import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords


def remove_punct(text):
    translator = str.maketrans("", "", string.punctuation)
    return text.translate(translator)


stop = set(stopwords.words("english"))
def remove_stopwords(text):
    filtered_words = [word.lower() for word in text.split() if word.lower() not in stop]
    return " ".join(filtered_words)


def main():
    data = pd.read_csv('dataset-Amazon.csv')

    columns = ['reviews.date', 'reviews.numHelpful', 'reviews.rating', 'reviews.doRecommend']
    string_columns = ['name', 'categories', 'primaryCategories', 'manufacturer', 'reviews.title',
                      'reviews.username', 'reviews.text']

    data = data[string_columns + columns]

    for c in string_columns:
        data[c] = data[c].str.lower()
        data[c] = data[c].map(remove_punct)
        data[c] = data[c].map(remove_stopwords)

    print("Empty rows summary:")
    print(data.isnull().sum())
    data.loc[(data["reviews.rating"] > 3), 'reviews.doRecommend'] = True
    data.loc[(data["reviews.rating"] <= 3), 'reviews.doRecommend'] = False
    data["reviews.doRecommend"] = data["reviews.doRecommend"].astype(int)
    print(data.isnull().sum())

    data.to_csv('data.csv')

    train, test = train_test_split(data, train_size=0.6, random_state=1)
    test, dev = train_test_split(test, test_size=0.5, random_state=1)

    test.to_csv('test.csv')
    train.to_csv('train.csv')
    dev.to_csv('dev.csv')

    print("\n\nMean reviews rating for each primary category: ")
    print(data[["primaryCategories", "reviews.rating"]].groupby("primaryCategories").mean())

    print("\n\nCounted primary categories: ")
    print(data["primaryCategories"].value_counts())

    print("\n\nGeneral data statistics: ")
    print(data.describe(include='all'))


if __name__ == '__main__':
    main()