pages/1_LAS_Exploratory.py

import pandas as pd
import matplotlib.pyplot as plt
import lasio, os
import numpy as np
import os
import streamlit as st

import altair as alt
from streamlit_vega_lite import altair_component

from io import StringIO

from ui import *
from Antuns.page_setting import page_intro
from mLogsFunctions import *
from mLogsFunctions.fx import *
#-----------------------------------------------------------------------------
page_intro()

#1_LOADINGDATA-----------------------------------------------------------------
st.write("Log ASCII standard (LAS) is a standard file format common in the oil-and-gas and water well industries to store well log information. Well logging is used to investigate and characterize the subsurface stratigraphy in a well.")
# pagetile = """<center><h1>LAS EXPLORATORY</h1></center>"""
# st.markdown(pagetile, unsafe_allow_html=True)
st.subheader('To begin using the app, load your LAS file using the file upload option below.')
st.subheader("1. LAS File Loading:")
#------------------------------------------------------------------------------
#Streamlit Dashboard------------------------------------------------------------------------------------------

# set_page_config(page='custom')
hide_menu_button()
condense_layout()
#-----------------------------------------------------------------------------
@st.cache_data() #allow_output_mutation=True, suppress_st_warning=True
def upload_las(uploaded_files):
    dataframes = {}
    las_data_list = []
    las_data = []
    if uploaded_files is not None:
        for file in uploaded_files:
            try:
                bytes_data = file.read()
                str_io = StringIO(bytes_data.decode('Windows-1252'))
                las_data = lasio.read(str_io)
                well_data = las_data.df()
                well_data['WELL'] = las_data.well.WELL.value
                if well_data.index.name == 'DEPT':
                    well_data.reset_index('DEPT', inplace=True)  # Set 'DEPT' as the new index
                    well_data.index.name = 'DEPT' 
                    if len(well_data) > 0:  # Kiểm tra xem dataframe có dữ liệu không
                        dataframes[file.name] = well_data
                        las_data_list.append(las_data)
                    else:
                        st.warning(f"No data in file {file.name}")
                else: 
                    well_data.index.name == 'DEPTH'
                    well_data.reset_index('DEPTH', inplace=True)  # Set 'DEPTH' as the new index
                    well_data.index.name = 'DEPTH' 
                    if len(well_data) > 0:  # Kiểm tra xem dataframe có dữ liệu không
                        dataframes[file.name] = well_data
                        las_data_list.append(las_data)                   
            except Exception as e:
                st.error(f"Error loading {file.name}: {e}")
    return dataframes, las_data_list, las_data

# Sidebar Options & File Upload
uploaded_files = st.file_uploader(label='Upload LAS files:', accept_multiple_files=True, type='las')

dataframes, las_data_list, las_data = upload_las(uploaded_files)
# print("print las data", las_data_list)
well_names = {}
if dataframes:
    merged_df = []
    for file_name, df in dataframes.items():
        well_name = file_name.split(".")[0]
        # Lấy danh sách các tên giếng
        well_names = list(dataframes.keys())

    # Cho phép người dùng chọn giếng và hiển thị DataFrame tương ứng
    selected_well = st.selectbox("Select Well", well_names, key = "selected_well_1")

    # st.write(f"Data for {selected_well}:")
    st.write(dataframes[selected_well])
    # Tạo một danh sách các DataFrame
    dfs = [df for _, df in dataframes.items()]
    merged_df = pd.concat([df for df in dfs])
    # Hiển thị DataFrame tổng thể
    st.write("Merged DataFrame:")
    st.write(merged_df)
else:
    print ("Please select LAS files for uploading ")
    st.warning('No valid LAS files were uploaded.')

curves = []
wellname = []
las = las_data
list_well = []
if las:
    
    for las_data in las_data_list:
        well_name = las_data.well['WELL'].value
        list_well.append(well_name)
        # print(list_well)

    st.success('File Uploaded Successfully')
    st.write(f'<b>Well Name</b>: {list_well}', unsafe_allow_html=True)
    # 2_CURVES_INFOMATION-----------------------------------------------------------------
    if las:
        
        st.subheader("2. Curve logs details:")
        selected_well = st.selectbox("Select Well", well_names, key = "selected_well_2")
        st.caption("All curve logs in data:")
        
        curves = []

        for well, las_file in zip(well_names, las_data_list):
            if well == selected_well:
                las = las_file
                break

    
        # print("in ra las:", las)
        for curve in las.curves:
            st.write(curve.mnemonic)
            curves.append(curve.mnemonic)

        for count, curve in enumerate(las.curves):
            st.write("---")
            st.write(f"Curve: {curve.mnemonic}, \t Units: {curve.unit}, \t Description: {curve.descr}")
            st.write(f"There are a total of: {count+1} curves present within this file")

    #3_DATAFRAME-----------------------------------------------------------------
        if "selected_well" not in st.session_state:
            st.session_state.selected_well = None
            st.session_state.selected_well_multi = None
        st.subheader("3. Converting LAS to DataFrame:")
        st.caption("3.1 Preview of all Dataframe")

        selected_well = st.selectbox("Select Well", well_names, key = "selected_well_5")
        # print("Well_name", well_names)
        # print("las_data_list", las_data_list)
        for well, las_file in zip(well_names, las_data_list):
            if well == selected_well:
                las = las_file
                break
            # break
        well = las.df()
        well['WELL'] = las.well.WELL.value
        well['DEPTH'] = well.index
        well = well.reset_index(drop=True)
        well = well.reindex(columns=['DEPTH'] + [col for col in well.columns if col != 'DEPTH'])
        st.write(well.head())
        st.caption("3.2 Well curves Statistics")
        st.write(well.describe())
        # print("in ra danh sách giếng", list_well)
        # create a selectbox to choose the well
    
    selected_well_multi = st.multiselect(" 3.3 Select well for download", list_well)
    st.session_state.changename = st.button("Create", key="create_curve")
    if st.session_state.changename:
        dataframes_df = pd.concat(dataframes.values(), ignore_index=True)
        st.session_state.selected_well_multi = dataframes_df.loc[dataframes_df['WELL'].isin(selected_well_multi)].reset_index(drop=True)
        st.dataframe(st.session_state.selected_well_multi)
        st.write(" Download DataFrame")
        st.download_button(label='Download CSV File',
                    data = st.session_state.selected_well_multi.to_csv(),
                    file_name=f"{selected_well_multi}.csv",
                    mime='text/csv')

    #4_Data Preprocessing-----------------------------------------------------------------
    st.subheader("4. Data Preprocessing:")
    st.session_state.old_name:str
    st.session_state.new_name:str
    st.session_state.changename:bool
    st.session_state.well = None

    st.write("4.1 Rename curves")

    st.session_state.selected_well_rename = None
    selected_well_rename = st.selectbox("Select Well", list_well, key="well_selectbox")

    well_to_las = {}
    well = []
    data_rename_1 =[]
    df_all_full = pd.DataFrame()
    st.session_state.selected_well_rename = None
    for i in range(len(well_names)):
        well_to_las[well_names[i]] = las_data_list[i]
        # print("key: ",well_names[i][:len(selected_well_rename)], " value: ",las_data_list[i])
        if  selected_well_rename == well_names[i][:len(selected_well_rename)]:
            las = las_data_list[i]
            break
        # print("In ra las:", las)
    well = las.df()
    well['WELL'] = las.well.WELL.value
    # print("In ra well2:", well)
    curves = well.columns.tolist()
    # print ("print ra cuvers:", curves) # save the number of curves for the selected well in session state
    st.session_state.num_curves = len(curves)
    df_rename = pd.DataFrame()
    st.session_state.selected_well_rename = df_rename
    st.session_state.selected_well_rename = well

import pandas as pd

# Khởi tạo DataFrame từ dữ liệu có sẵn
# Khởi tạo thuộc tính selected_well_rename trong st.session_state
st.session_state.setdefault('selected_well_rename', 'Default value')
# Truy cập thuộc tính selected_well_rename

data = st.session_state.selected_well_rename 
if 'columns' in data:
    n_cols = 4
    n_rows = -(-len(data.columns) // n_cols)  # Round up division
    for i in range(n_rows):
        cols = st.columns(n_cols)
        for j in range(n_cols):
            idx = i * n_cols + (j-1)
            if idx < len(data.columns):
                col = data.columns[idx]
                # Lưu trữ tên cũ trong biến old_col
                old_col = col
                # new_col == well_names[i][:len(col)]
                new_col = cols[j-1].text_input(f"Enter new name for '{col}'", key=f"input_{cols}")
                # Kiểm tra nếu người dùng không nhập tên mới
                if not new_col:
                    # Sử dụng tên cũ thay thế
                    new_col = old_col
                data = data.rename(columns={col: new_col})
                data["DEPTH"] = well.index
                data.insert(0, 'DEPTH', data.pop('DEPTH'))
                data = data.reset_index(drop=True)
                st.dataframe(data)
else:
    print ("Please select LAS files for input data")
# Hiển thị lại bảng

def my_function(data):
    # Lưu trữ DataFrame khi người dùng nhấn vào nút "Lưu"
    if st.button("Lưu", key="saved_rename"):
        # Tạo tên file CSV dựa trên biến selected_well_rename
        file_name = f"/work/2022_VPIMLogs_WebApp/data/change_name_logs/{selected_well_rename}.csv"
        # Lưu trữ DataFrame vào tệp CSV với tên file tương ứng
        data.to_csv(file_name, index=False)
    # Trả về giá trị của biến result
    return data
result = my_function(data)

# for name in selected_well_multi:
#     # dataframe_merged_df = pd.DataFrame()
#     merged_df = pd.read_csv("data/change_name_logs/merged_df.csv")
#     dataframe_merged_df.append(merged_df[merged_df.WELL==name])
#     dataframe_merged_df.to_csv("data/change_name_logs/merged_df.csv")
#     st.dataframe(dataframe_merged_df, width=1400)


selected_well_multi= st.multiselect(" 4.3 Select well for download", list_well, key = 'selected_well_multi_lasts')  
# dowload_dataframes_df = pd.DataFrame()
st.session_state.changename_download = st.button("Create", key="selected_well_multi_rename_curve_111")
# Đường dẫn đến thư mục chứa các file csv
dir_path = '/work/2022_VPIMLogs_WebApp/data/change_name_logs/'
if st.session_state.changename_download:
    # Tạo một DataFrame rỗng để chứa dữ liệu
    merged_df = pd.DataFrame()
    dataframe_merged_df = pd.DataFrame()
    # Duyệt qua tất cả các file trong thư mục và gộp chúng vào DataFrame
    for filename in os.listdir(dir_path):
        if filename.endswith('.csv'):
            filepath = os.path.join(dir_path, filename)
            df = pd.read_csv(filepath)
            merged_df = pd.concat([merged_df, df], ignore_index=True).reset_index(drop=True)
        merged_df.to_csv(f"/work/2022_VPIMLogs_WebApp/data/merged/{selected_well_multi}_merged_df.csv")
    dataframes_df = pd.read_csv(f"/work/2022_VPIMLogs_WebApp/data/merged/{selected_well_multi}_merged_df.csv")
    st.session_state.selected_well_multi = dataframes_df.loc[dataframes_df['WELL'].isin(selected_well_multi)].reset_index(drop=True).drop('Unnamed: 0', axis = 1)
    
    st.dataframe(st.session_state.selected_well_multi , width=1400)
        # 4.3_DOWNLOAD-----------------------------------------------------------------
    st.write("4.3 Download well curves with renamed names")
    st.download_button(label='Download CSV File',
                data = st.session_state.selected_well_multi.to_csv(),
                file_name=f"{selected_well_multi}.csv",
                mime='text/csv')
    for filename in os.listdir(dir_path):
        if filename.endswith('.csv'):
            os.remove(os.path.join(dir_path, filename))
#'''Adding the ‘download’ tag attribute as shown below allows you to provide a file name and extension.
#f'<a href="data:file/csv;base64,{b64}" download="myfilename.csv">Download csv file</a>'''

hide_menu_button()
condense_layout()