Spaces:
Runtime error
Runtime error
Download data_prep.py from Silverxwolf/FoodQast: direct link, hf CLI and curl.
- Browser
- Download file 4.57 kB
-
https://huggingface.co/spaces/Silverxwolf/FoodQast/resolve/main/data_prep.py
- Command line
-
hf download hf://spaces/Silverxwolf/FoodQast/data_prep.py
-
curl -L -o data_prep.py https://huggingface.co/spaces/Silverxwolf/FoodQast/resolve/main/data_prep.py
4.57 kB
| import streamlit as st | |
| import pandas as pd | |
| from datetime import timedelta | |
| def get_frequency(datasets, columns, load_options): | |
| freq_options = _frequency_options(datasets["data"], columns) | |
| frequency = st.selectbox("", freq_options, label_visibility="collapsed", index=1) | |
| #frequency settings | |
| if frequency == "Daily": | |
| freq = "D" | |
| freq_label = "days" | |
| elif frequency == "Hourly": | |
| freq = "H" | |
| freq_label = "hours" | |
| elif frequency == "Weekly": | |
| freq = "W" | |
| freq_label = "weeks" | |
| load_options["frequency"] = frequency | |
| load_options["freq"] = freq | |
| load_options["freq_label"] = freq_label | |
| return load_options | |
| def tmp_renaming_columns(datasets, columns, load_options): | |
| #renaming columns | |
| datasets["data"].rename(columns={columns["date_column"]: 'date'}, inplace=True) | |
| datasets["data"] = datasets["data"].sort_values(by='date', ascending=True) | |
| if load_options["two_files"]: | |
| datasets["data"]['food_amount'] = datasets["data"][columns["quantity_column"]] * datasets["data"][columns["quantity_per_item_column"]] | |
| else: | |
| datasets["data"].rename(columns={columns["quantity_column"]: 'food_amount'}, inplace=True) | |
| # returns frequency options available for forecast | |
| def _frequency_options(data, columns): | |
| contains_hours = (data[columns['date_column']].dt.hour != 0).any() | |
| contains_minutes = (data[columns['date_column']].dt.minute != 0).any() | |
| contains_seconds = (data[columns['date_column']].dt.second != 0).any() | |
| if contains_hours or contains_minutes or contains_seconds: | |
| return ["Hourly", "Daily", "Weekly"] | |
| elif columns["time_column"] != "<None>": | |
| return ["Hourly", "Daily", "Weekly"] | |
| return ["Daily", "Weekly"] | |
| def get_dates(food_df): | |
| dates = dict() | |
| # Calculate initial_split_date as a Python datetime object | |
| initial_split_date = (food_df['date'].iloc[-1] - pd.DateOffset(weeks=4)).to_pydatetime() | |
| # Convert the Timestamp objects to Python datetime objects | |
| min_date = food_df['date'].min().to_pydatetime() | |
| max_date = food_df['date'].max().to_pydatetime() | |
| # Use Python datetime objects in the st.slider | |
| training_slider = st.slider( | |
| "Select the training data range:", | |
| value=(food_df['date'].iloc[0].to_pydatetime(), initial_split_date), | |
| min_value=min_date, | |
| max_value=max_date - timedelta(days=1) | |
| ) | |
| dates["train_start"], dates["train_end"] = training_slider | |
| # How many points in the future to predict | |
| test_intitial = dates["train_end"] + timedelta(days=1) | |
| testing_slider = st.slider( | |
| "Select the testing data range:", | |
| value=(test_intitial, max_date), | |
| min_value=test_intitial, | |
| max_value=max_date | |
| ) | |
| dates["test_start"], dates["test_end"] = testing_slider | |
| return dates | |
| def split_dataset(food_df, dates): | |
| # splitting data | |
| train_df = food_df[(food_df["date"] >= dates["train_start"]) & (food_df["date"] <= dates["train_end"])].copy() | |
| test_df = food_df[(food_df["date"] >= dates["test_start"]) & (food_df["date"] <= dates["test_end"])].copy() | |
| _display_dates(train_df, test_df) | |
| return train_df, test_df | |
| # display number of days in each split | |
| def _display_dates(train_df, test_df): | |
| training_duration = train_df['date'].max() - train_df['date'].min() | |
| training_days = training_duration.days | |
| testing_duration = test_df['date'].max() - test_df['date'].min() | |
| testing_days = testing_duration.days | |
| st.success(f''' | |
| Training Period: {training_days} days | |
| Testing Period: {testing_days} days | |
| ''') | |
| def get_forecast_dates(food_df, load_options): | |
| duration = st.number_input(f"Forecast length in {load_options['freq_label']}", | |
| min_value=1, max_value= 100, value=5) | |
| load_options["duration"] = duration | |
| min_date = food_df['date'].min().to_pydatetime() | |
| max_date = food_df['date'].max().to_pydatetime() | |
| forecast_slider = st.slider( | |
| "Select forecast training data range:", | |
| value=(food_df['date'].iloc[0].to_pydatetime(), max_date), | |
| min_value=min_date, | |
| max_value=max_date | |
| ) | |
| train_start, train_end = forecast_slider | |
| forecast_df = food_df[(food_df["date"] >= train_start) & (food_df["date"] <= train_end)].copy() | |
| return forecast_df, load_options |