Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| from textclassifier import TextClassifier as tc | |
| from functions import * | |
| import re | |
| def main(from_date, to_date, user_name): | |
| """ | |
| Main function. Runs the program. | |
| :return: None | |
| """ | |
| from_date = from_date | |
| to_date = to_date | |
| user_name = user_name | |
| text_classifier = tc.TextClassifier(from_date=from_date, to_date=to_date, user_name=user_name, num_tweets=20) | |
| text_classifier.run_main_pipeline() | |
| dataframe = text_classifier.dataframe | |
| return (dataframe, get_summary_statistics(dataframe)) | |
| def get_summary_statistics(dataframe): | |
| """ | |
| This function returns a summary statistics of the dataframe. Returns a string with the summary statistics. | |
| :param dataframe: dataframe | |
| :return: str | |
| """ | |
| summary_statistics = dataframe.describe() | |
| return summary_statistics.to_string() | |
| def separate_string(string): | |
| list_string = string.split('.') | |
| list_useable = [] | |
| for list_part in list_string : | |
| list_useable.append(list_part.split(' ', 1)) | |
| final_list = [] | |
| for li in list_useable[1:]: | |
| final_list.append(li[1]) | |
| # remove numeric characters and spaces | |
| filter_numeric_regex = '[^a-z]' | |
| final_final_list = [] | |
| for li in final_list: | |
| final_final_list.append(re.sub(filter_numeric_regex,' ',li).strip()) | |
| return final_final_list | |
| def summary_categorical(dataframe): | |
| """ | |
| This function returns a string of a summary of categorical variables of a dataframe | |
| :param dataframe: | |
| :return: | |
| """ | |
| # First find all numeric columns in the dataframe | |
| numeric_columns = dataframe._get_numeric_data().columns | |
| # Then find all categorical columns in the dataframe | |
| categorical_columns = dataframe.select_dtypes(include=['object']).columns | |
| print("Numeric columns: " + str(numeric_columns) + "\n" + "Categorical columns: " + str(categorical_columns)) | |
| # Then find the summary statistics of each categorical column | |
| summary = "" | |
| for column in categorical_columns: | |
| # skip 'tweet', 'urls' and 'date' columns | |
| if column == 'tweet' or column == 'date' or column == 'urls': | |
| continue | |
| else: | |
| summary += column + ": " + str(dataframe[column].value_counts()) + "\n" | |
| # Return a nice decoration of summary | |
| return "Summary of categorical variables:\n" + summary | |
| if __name__ == "__main__": | |
| from datetime import date | |
| # demo = gr.Interface( | |
| # fn=main, | |
| # inputs=['text', 'text', 'text'], | |
| # outputs=["dataframe", "text"], | |
| # ) | |
| # demo.launch() | |
| text_classifier = tc.TextClassifier(from_date='2020-01-01', to_date='2020-01-31', user_name="jimmieakesson", | |
| num_tweets=20) | |
| text_classifier.run_main_pipeline() | |
| print(get_summary_statistics(text_classifier.get_dataframe())) | |
| print(type(get_summary_statistics(text_classifier.get_dataframe()))) | |
| print(summary_categorical(text_classifier.get_dataframe())) | |
| string = '1. swedish 2. nuclear 3. hello world 4. uha yhd ikv hahd vva 5. ' | |
| print(separate_string(string)) | |