FoodQast / format.py
Silverxwolf's picture
Upload 12 files
ca8bb53
Raw History Blame Contribute Delete
4.63 kB
from typing import Any, Dict, List, Tuple
import numpy as np
import pandas as pd
import streamlit as st
def validate_and_formate_columns(datasets, columns, load_options):
_validate_selection(columns, load_options)
datasets = _validate_date_and_format(datasets, columns["date_column"], load_options)
_validate_numeric(datasets, columns["quantity_column"])
datasets = _combine_datetime(datasets, columns)
datasets = _merge_files(datasets, columns, load_options)
def filter_selected_options(datasets, columns, load_options):
data = datasets["data"]
if load_options.get("forecast_item") != None:
data = data[data[columns["item_column"]] == load_options["forecast_item"]]
data = data.reset_index(drop=True)
if load_options.get("forecast_branch") != None:
data = data[data[columns["branch_column"]] == load_options["forecast_branch"]]
data = data.reset_index(drop=True)
datasets["data"] = data
return datasets
def valid_rows_number(datasets, load_options):
if load_options["forecast"]:
if len(datasets["forecast_df"]) < 5:
st.sidebar.error("The number of rows should be 5 or more to forecast.")
st.session_state.clicked = False
st.stop()
elif load_options["evaluate"]:
if len(datasets["train_df"]) < 5:
st.sidebar.error("The number of rows should be 5 or more to forecast.")
st.session_state.clicked = False
st.stop()
# if there are two seperate files, merge them
def _merge_files(datasets, columns, load_options):
if load_options["two_files"]:
try:
datasets["data"] = pd.merge(datasets["recipe_data"],
datasets["data"],
left_on=columns["recipe_column"],
right_on=columns["sale_column"])
except Exception as e:
st.sidebar.error("Cannot merge the two files, make sure the correct ID columns are selected.")
st.session_state.clicked = False
st.stop()
return datasets
# Combine date and time if in seperate columns
def _combine_datetime(datasets, columns):
data = datasets["data"]
if columns["time_column"] != '<None>':
if pd.api.types.is_numeric_dtype(data[columns["time_column"]]):
data[columns["date_column"]] = data[columns["date_column"]] + pd.to_timedelta(data[columns["time_column"]], unit='H')
else:
try:
data[columns["time_column"]] = pd.to_datetime(data[columns["time_column"]]).dt.time
data[columns["date_column"]] = data.apply(lambda x: pd.datetime.combine(x[columns["date_column"]], x[columns["time_column"]]), axis=1)
except Exception as e:
st.sidebar.error("Time column is not in datetime format.")
st.session_state.clicked = False
st.stop()
datasets["data"] = data
return datasets
def _validate_selection(columns, load_options):
if columns["quantity_column"]=='<None>' or columns["date_column"]=='<None>':
st.sidebar.warning("Select all of the required columns.")
st.session_state.clicked = False
st.stop()
if load_options["two_files"]:
if (columns["quantity_per_item_column"]=='<None>' or
columns["recipe_column"]=='<None>' or
columns["sale_column"]=='<None>'):
st.sidebar.warning("Select all of the required columns.")
st.session_state.clicked = False
st.stop()
def _validate_numeric(datasets, column):
data = datasets["data"]
if not pd.api.types.is_numeric_dtype(data[column]):
st.sidebar.error(f"{column} is not a numeric column.")
st.session_state.clicked = False
st.stop()
def _validate_date_and_format(datasets, column, load_options):
data = datasets["data"]
if not pd.api.types.is_datetime64_any_dtype(data[column]):
if pd.api.types.is_numeric_dtype(data[column]):
st.write("point 1")
st.sidebar.error(f"{column} is not in datetime format.")
st.session_state.clicked = False
st.stop()
try:
data[column] = pd.to_datetime(data[column], **load_options["date_params"])
except Exception as e:
st.sidebar.error(f"{column} is not in datetime format.")
st.session_state.clicked = False
st.stop()
datasets["data"] = data
return datasets