Model_Result_Overview.py

import streamlit as st
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
import pickle
import Streamlit_functions as sf
from utilities import load_authenticator

from utilities_with_panel import (set_header,
                                  overview_test_data_prep_panel,
                                  overview_test_data_prep_nonpanel,
                                  initialize_data,
                                  load_local_css,
                                  create_channel_summary,
                                  create_contribution_pie,
                                  create_contribuion_stacked_plot,
                                  create_channel_spends_sales_plot,
                                  format_numbers,
                                  channel_name_formating)

import plotly.graph_objects as go
import streamlit_authenticator as stauth
import yaml
from yaml import SafeLoader
import time
from datetime import datetime

st.set_page_config(layout='wide')
load_local_css('styles.css')
set_header()


def get_random_effects(media_data, panel_col, mdf):
    random_eff_df = pd.DataFrame(columns=[panel_col, "random_effect"])

    for i, market in enumerate(media_data[panel_col].unique()):
        print(i, end='\r')
        intercept = mdf.random_effects[market].values[0]
        random_eff_df.loc[i, 'random_effect'] = intercept
        random_eff_df.loc[i, panel_col] = market

    return random_eff_df


def process_train_and_test(train, test, features, panel_col, target_col):
    X1 = train[features]

    ss = MinMaxScaler()
    X1 = pd.DataFrame(ss.fit_transform(X1), columns=X1.columns)

    X1[panel_col] = train[panel_col]
    X1[target_col] = train[target_col]

    if test is not None:
        X2 = test[features]
        X2 = pd.DataFrame(ss.transform(X2), columns=X2.columns)
        X2[panel_col] = test[panel_col]
        X2[target_col] = test[target_col]
        return X1, X2
    return X1

def mdf_predict(X_df, mdf, random_eff_df) :
    X=X_df.copy()
    X=pd.merge(X, random_eff_df[[panel_col,'random_effect']], on=panel_col, how='left')
    X['pred_fixed_effect'] = mdf.predict(X)

    X['pred'] = X['pred_fixed_effect'] + X['random_effect']
    X.to_csv('Test/merged_df_contri.csv',index=False)
    X.drop(columns=['pred_fixed_effect', 'random_effect'], inplace=True)

    return X


target_col='Prospects'
target='Prospects'

# is_panel=False
# is_panel = st.session_state['is_panel']
#panel_col = [col.lower().replace('.','_').replace('@','_').replace(" ", "_").replace('-', '').replace(':', '').replace("__", "_") for col in  st.session_state['bin_dict']['Panel Level 1']  ] [0]# set the panel column
panel_col='Panel'
date_col = 'date'

#st.write(media_data)

is_panel = True 

# panel_col='markets'
date_col = 'date'
for k, v in st.session_state.items():

    if k not in ['logout', 'login','config'] and not k.startswith('FormSubmitter'):
        st.session_state[k] = v

authenticator = st.session_state.get('authenticator')

if authenticator is None:
    authenticator = load_authenticator()
    
name, authentication_status, username = authenticator.login('Login', 'main')
auth_status = st.session_state['authentication_status']

if auth_status:
    authenticator.logout('Logout', 'main')
    
    is_state_initiaized = st.session_state.get('initialized',False)
    if not is_state_initiaized:
        a=1
    
    # st.header("")
    st.markdown("<h5 style='font-weight: normal;'>MMM Readout for Selected Period</h5>", unsafe_allow_html=True)
    #### Input Select Start and End Date  
    
    # Create two columns for start date and end date input
    col1, col2 = st.columns(2)
                                                                
    with col1:
        default_date = datetime(2024, 1, 28)
        start_date = st.date_input("Start Date: ",value=default_date)
        
    with col2:
        default_date = datetime(2024, 2, 24)
        end_date = st.date_input("End Date: ",value=default_date)
    
    # col1, col2 = st.columns(2)
    # with col1:
    #     fig = sf.pie_spend(start_date,end_date)
    #     st.plotly_chart(fig,use_container_width=True)
    # with col2:
    #     fig = sf.pie_contributions(start_date,end_date)
    #     st.plotly_chart(fig,use_container_width=True)
    # st.header("Distribution of Spends and Contributions")
    fig = sf.pie_charts(start_date,end_date)
    st.plotly_chart(fig,use_container_width=True)

    # Dropdown menu options
    options = [
        "Month on Month",
        "Year on Year"]
    col1, col2 = st.columns(2)
         # Create a dropdown menu
    with col1:
        selected_option = st.selectbox('Select a comparison', options)
    with col2:
        st.write("")
        # Waterfall chart
    fig = sf.waterfall(start_date,end_date,selected_option)
    st.plotly_chart(fig,use_container_width=True)
        
    # Waterfall table
    shares_df = sf.shares_df_func(start_date,end_date)
    st.table(sf.waterfall_table_func(shares_df).style.format("{:.0%}"))

    ## Channel Contribution Bar Chart
    st.plotly_chart(sf.channel_contribution(start_date,end_date),use_container_width=True)
    # Format first three rows in percentage format
    # styled_df = sf.shares_table_func(shares_df)
    # # styled_df = styled_df.round(0).astype(int)
    # styled_df.iloc[:3] = (styled_df.iloc[:3]).astype(int)

        # # Round next two rows to two decimal places
        # styled_df.iloc[3:5] = styled_df.iloc[3:5].round(0).astype(str)

        # st.table(styled_df)
    st.dataframe(sf.shares_table_func(shares_df),use_container_width=True)

    st.dataframe(sf.eff_table_func(shares_df),use_container_width=True)

        ### CPP CHART
    st.plotly_chart(sf.cpp(start_date,end_date),use_container_width=True)
        
        ### Base decomp CHART
    st.plotly_chart(sf.base_decomp(),use_container_width=True)

        ### Media decomp CHART
    st.plotly_chart(sf.media_decomp(),use_container_width=True)
     
    
    # st.write(fig.columns)
    # st.dataframe(fig)

    # def panel_fetch(file_selected):
    #     raw_data_mmm_df = pd.read_excel(file_selected, sheet_name="RAW DATA MMM")

    #     if "Panel" in raw_data_mmm_df.columns:
    #         panel = list(set(raw_data_mmm_df["Panel"]))
    #     else:
    #         raw_data_mmm_df = None
    #         panel = None

    #     return panel

    # def rerun():
    #     st.rerun()

    # metrics_selected='prospects'

    # file_selected = (
    #         f"Overview_data_test_panel@#{metrics_selected}.xlsx"
    #     )
    # panel_list = panel_fetch(file_selected)

    # if "selected_markets" not in st.session_state:
    #     st.session_state['selected_markets']='DMA1'


    # st.header('Overview of previous spends')

    # selected_market= st.selectbox(
    #         "Select Markets",
    #         ["Total Market"] + panel_list
    #     )



    # initialize_data(target_col,selected_market)
    # scenario = st.session_state['scenario']
    # raw_df = st.session_state['raw_df']
    # st.write(scenario.actual_total_spends)
    # st.write(scenario.actual_total_sales)
    # columns = st.columns((1,1,3))

    # with columns[0]:
    #     st.metric(label='Spends', value=format_numbers(float(scenario.actual_total_spends)))
    # ###print(f"##################### {scenario.actual_total_sales} ##################")
    # with columns[1]:
    #     st.metric(label=target, value=format_numbers(float(scenario.actual_total_sales),include_indicator=False))


    # actual_summary_df = create_channel_summary(scenario)
    # actual_summary_df['Channel'] = actual_summary_df['Channel'].apply(channel_name_formating) 

    # columns = st.columns((2,1))
    # #with columns[0]:
    # with st.expander('Channel wise overview'):
    #     st.markdown(actual_summary_df.style.set_table_styles(
    #     [{
    #         'selector': 'th',
    #         'props': [('background-color', '#FFFFF')]
    #     },
    #         {
    #         'selector' : 'tr:nth-child(even)',
    #         'props' : [('background-color', '#FFFFF')]
    #         }]).to_html(), unsafe_allow_html=True)
            
    # st.markdown("<hr>",unsafe_allow_html=True)
    # ##############################

    # st.plotly_chart(create_contribution_pie(scenario),use_container_width=True)
    # st.markdown("<hr>",unsafe_allow_html=True)


    # ################################3
    # st.plotly_chart(create_contribuion_stacked_plot(scenario),use_container_width=True)
    # st.markdown("<hr>",unsafe_allow_html=True)
    # #######################################

    # selected_channel_name = st.selectbox('Channel', st.session_state['channels_list'] + ['non media'], format_func=channel_name_formating)
    # selected_channel = scenario.channels.get(selected_channel_name,None)

    # st.plotly_chart(create_channel_spends_sales_plot(selected_channel), use_container_width=True)

    # st.markdown("<hr>",unsafe_allow_html=True)

# elif auth_status == False:
#     st.error('Username/Password is incorrect')
    
# if auth_status != True:
#     try:
#         username_forgot_pw, email_forgot_password, random_password = authenticator.forgot_password('Forgot password')
#         if username_forgot_pw:
#             st.success('New password sent securely')
#             # Random password to be transferred to user securely
#         elif username_forgot_pw == False:
#             st.error('Username not found')
#     except Exception as e:
#         st.error(e)
# st.header("")
# st.markdown("<h5 style='font-weight: normal;'>MMM Readout for Selected Period</h5>", unsafe_allow_html=True)
# #### Input Select Start and End Date
    
# # Create two columns for start date and end date input
# col1, col2 = st.columns(2)
    
# with col1:
#     start_date = st.date_input("Start Date: ")
    
# with col2:
#     end_date = st.date_input("End Date: ")
# # Dropdown menu options
# options = [
#     "Month on Month",
#     "Year on Year"]
# col1, col2 = st.columns(2)
#      # Create a dropdown menu
# with col1:
#     selected_option = st.selectbox('Select a comparison', options)
# with col2:
#     st.write("")
#     # Waterfall chart
# fig = sf.waterfall(start_date,end_date,selected_option)
# st.plotly_chart(fig)
    
# # Waterfall table
# shares_df = sf.shares_df_func(start_date,end_date)
# st.table(sf.waterfall_table_func(shares_df).style.format("{:.0%}"))

# ## Channel Contribution Bar Chart
# st.plotly_chart(sf.channel_contribution(start_date,end_date))
# # Format first three rows in percentage format
# # styled_df = sf.shares_table_func(shares_df)
# # # styled_df = styled_df.round(0).astype(int)
# # styled_df.iloc[:3] = (styled_df.iloc[:3]).astype(int)

#     # # Round next two rows to two decimal places
#     # styled_df.iloc[3:5] = styled_df.iloc[3:5].round(0).astype(str)

#     # st.table(styled_df)
# st.dataframe(sf.shares_table_func(shares_df))

# st.dataframe(sf.eff_table_func(shares_df))

#     ### CPP CHART
# st.plotly_chart(sf.cpp(start_date,end_date))
    
#     ### Base decomp CHART
# st.plotly_chart(sf.base_decomp())

#     ### Media decomp CHART
#     st.plotly_chart(sf.media_decomp())