mLogsFunctions/dataloading.py

import pandas as pd
import streamlit as st

def csv_uploader(label:str='', type:str='csv'):
    uploaded_file = st.file_uploader(label=label, type=type)
    loading_data = None
    if uploaded_file is not None:
        if type == 'csv':
            loading_data = pd.read_csv(uploaded_file, na_values=-9999)
    return loading_data

@st.cache_data
def tweak_data(data, reindex:bool=True, resample:bool=False, max_number:int=5000):
    if data is not None:
        data = data.rename(str.upper, axis='columns')
        if len(data) > max_number and resample:
            data = data.sample(max_number, random_state=42)
        if set(["DEPTH", 'WELL']).issubset(data.columns.unique()):
            data.assign(
                        DEPTH=data.DEPTH.astype('float64'),
                        WELL=data.WELL.astype("string"),
                        )
        if "FRACTURE_ZONE" in data.columns.unique():
            data = data.rename(columns={'FRACTURE_ZONE':'FRACTUREZONE'})
        if "FRACTURE INTENSITY" in data.columns.unique():
            data = data.rename(columns={'FRACTURE INTENSITY':'FRACTURE_INTENSITY'})
        # if "FRACTUREZONE" in data.columns.unique():
            # data = data.reset_index(drop=True).drop(["FRACTUREZONE"], axis=1)
        if reindex:
            data = data.reindex(sorted(data.columns), axis=1) #Reindex and sort columns name
    return data