""" MMO Build Sprint 3 additions : adding more variables to session state for saved model : random effect, predicted train & test MMO Build Sprint 4 additions : ability to run models for different response metrics """ import streamlit as st import pandas as pd import plotly.express as px import plotly.graph_objects as go from Eda_functions import format_numbers import numpy as np import pickle from st_aggrid import AgGrid from st_aggrid import GridOptionsBuilder, GridUpdateMode from utilities import set_header, load_local_css from st_aggrid import GridOptionsBuilder import time import itertools import statsmodels.api as sm import numpy as npc import re import itertools from sklearn.metrics import ( mean_absolute_error, r2_score, mean_absolute_percentage_error, ) from sklearn.preprocessing import MinMaxScaler import os import matplotlib.pyplot as plt from statsmodels.stats.outliers_influence import variance_inflation_factor import yaml from yaml import SafeLoader import streamlit_authenticator as stauth st.set_option("deprecation.showPyplotGlobalUse", False) import statsmodels.api as sm import statsmodels.formula.api as smf from datetime import datetime import seaborn as sns from Data_prep_functions import * import sqlite3 from utilities import update_db from datetime import datetime, timedelta @st.cache_resource(show_spinner=False) # def save_to_pickle(file_path, final_df): # # Open the file in write-binary mode and dump the objects # with open(file_path, "wb") as f: # pickle.dump({file_path: final_df}, f) @st.cache_resource(show_spinner=True) def prepare_data_df(data): data = data[data["pos_count"] == data["pos_count"].max()].reset_index( drop=True ) # Sprint4 -- Srishti -- only show models with the lowest num of neg coeffs data.sort_values(by=["ADJR2"], ascending=False, inplace=True) data.drop_duplicates(subset="Model_iteration", inplace=True) # Applying the function to each row in the DataFrame data["coefficients"] = data["coefficients"].apply(process_dict) # Convert dictionary items into separate DataFrame columns coefficients_df = data["coefficients"].apply(pd.Series) # Rename the columns to remove any trailing underscores and capitalize the words coefficients_df.columns = [ col.strip("_").replace("_", " ").title() for col in coefficients_df.columns ] # Normalize each row so that the sum equals 100% coefficients_df = coefficients_df.apply( lambda x: round((x / x.sum()) * 100, 2), axis=1 ) # Join the new columns back to the original DataFrame data = data.join(coefficients_df) data_df = data[ [ "Model_iteration", "MAPE", "ADJR2", "R2", "Total Positive Contributions", "Significance", ] + list(coefficients_df.columns) ] data_df.rename(columns={"Model_iteration": "Model Iteration"}, inplace=True) data_df.insert(0, "Rank", range(1, len(data_df) + 1)) return coefficients_df, data_df def format_display(inp): return inp.title().replace("_", " ").strip() 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 mdf_predict(X_df, mdf, random_eff_df): X = X_df.copy() X["fixed_effect"] = mdf.predict(X) X = pd.merge(X, random_eff_df, on=panel_col, how="left") X["pred"] = X["fixed_effect"] + X["random_effect"] # X.to_csv('Test/megred_df.csv',index=False) X.drop(columns=["fixed_effect", "random_effect"], inplace=True) return X["pred"] st.set_page_config( page_title="Model Build", page_icon=":shark:", layout="wide", initial_sidebar_state="collapsed", ) load_local_css("styles.css") set_header() # Check for authentication status for k, v in st.session_state.items(): if k not in [ "logout", "login", "config", "model_build_button", ] and not k.startswith("FormSubmitter"): st.session_state[k] = v with open("config.yaml") as file: config = yaml.load(file, Loader=SafeLoader) st.session_state["config"] = config authenticator = stauth.Authenticate( config["credentials"], config["cookie"]["name"], config["cookie"]["key"], config["cookie"]["expiry_days"], config["preauthorized"], ) st.session_state["authenticator"] = authenticator name, authentication_status, username = authenticator.login("Login", "main") auth_status = st.session_state.get("authentication_status") if auth_status == True: authenticator.logout("Logout", "main") is_state_initiaized = st.session_state.get("initialized", False) conn = sqlite3.connect( r"DB/User.db", check_same_thread=False ) # connection with sql db c = conn.cursor() if not is_state_initiaized: if "session_name" not in st.session_state: st.session_state["session_name"] = None if "project_dct" not in st.session_state: st.error("Please load a project from Home page") st.stop() st.title("1. Build Your Model") if not os.path.exists( os.path.join(st.session_state["project_path"], "data_import.pkl") ): st.error("Please move to Data Import Page and save.") st.stop() with open( os.path.join(st.session_state["project_path"], "data_import.pkl"), "rb" ) as f: data = pickle.load(f) st.session_state["bin_dict"] = data["bin_dict"] if not os.path.exists( os.path.join( st.session_state["project_path"], "final_df_transformed.pkl" ) ): st.error( "Please move to Transformation Page and save transformations." ) st.stop() with open( os.path.join( st.session_state["project_path"], "final_df_transformed.pkl" ), "rb", ) as f: data = pickle.load(f) media_data = data["final_df_transformed"] # Sprint4 - available response metrics is a list of all reponse metrics in the data ## these will be put in a drop down st.session_state["media_data"] = media_data if "available_response_metrics" not in st.session_state: # st.session_state['available_response_metrics'] = ['Total Approved Accounts - Revenue', # 'Total Approved Accounts - Appsflyer', # 'Account Requests - Appsflyer', # 'App Installs - Appsflyer'] st.session_state["available_response_metrics"] = st.session_state[ "bin_dict" ]["Response Metrics"] # Sprint4 if "is_tuned_model" not in st.session_state: st.session_state["is_tuned_model"] = {} for resp_metric in st.session_state["available_response_metrics"]: resp_metric = ( resp_metric.lower() .replace(" ", "_") .replace("-", "") .replace(":", "") .replace("__", "_") ) st.session_state["is_tuned_model"][resp_metric] = False # Sprint4 - used_response_metrics is a list of resp metrics for which user has created & saved a model if "used_response_metrics" not in st.session_state: st.session_state["used_response_metrics"] = [] # Sprint4 - saved_model_names if "saved_model_names" not in st.session_state: st.session_state["saved_model_names"] = [] if "Model" not in st.session_state: if ( "session_state_saved" in st.session_state["project_dct"]["model_build"].keys() and st.session_state["project_dct"]["model_build"][ "session_state_saved" ] is not None and "Model" in st.session_state["project_dct"]["model_build"][ "session_state_saved" ].keys() ): st.session_state["Model"] = st.session_state["project_dct"][ "model_build" ]["session_state_saved"]["Model"] else: st.session_state["Model"] = {} date_col = "date" date = media_data[date_col] # Sprint4 - select a response metric default_target_idx = ( st.session_state["project_dct"]["model_build"].get( "sel_target_col", None ) if st.session_state["project_dct"]["model_build"].get( "sel_target_col", None ) is not None else st.session_state["available_response_metrics"][0] ) start_cols = st.columns(2) min_date = min(date) max_date = max(date) with start_cols[0]: sel_target_col = st.selectbox( "Select the response metric", st.session_state["available_response_metrics"], index=st.session_state["available_response_metrics"].index( default_target_idx ), format_func=format_display ) # , on_change=reset_save()) st.session_state["project_dct"]["model_build"][ "sel_target_col" ] = sel_target_col default_test_start = min_date + (3*(max_date-min_date)/4) with start_cols[1]: test_start = st.date_input( "Select test start date", default_test_start, min_value=min_date, max_value=max_date, ) train_idx = media_data[media_data[date_col] <= pd.to_datetime(test_start)].index[-1] # st.write(train_idx, media_data.index[-1]) target_col = ( sel_target_col.lower() .replace(" ", "_") .replace("-", "") .replace(":", "") .replace("__", "_") ) new_name_dct = { col: col.lower() .replace(".", "_") .lower() .replace("@", "_") .replace(" ", "_") .replace("-", "") .replace(":", "") .replace("__", "_") for col in media_data.columns } media_data.columns = [ col.lower() .replace(".", "_") .replace("@", "_") .replace(" ", "_") .replace("-", "") .replace(":", "") .replace("__", "_") for col in media_data.columns ] 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 is_panel = True if len(panel_col) > 0 else False if "is_panel" not in st.session_state: st.session_state["is_panel"] = is_panel if is_panel: media_data.sort_values([date_col, panel_col], inplace=True) else: media_data.sort_values(date_col, inplace=True) media_data.reset_index(drop=True, inplace=True) st.session_state["date"] = date y = media_data[target_col] if is_panel: spends_data = media_data[ [ c for c in media_data.columns if "_cost" in c.lower() or "_spend" in c.lower() ] + [date_col, panel_col] ] # Sprint3 - spends for resp curves else: spends_data = media_data[ [ c for c in media_data.columns if "_cost" in c.lower() or "_spend" in c.lower() ] + [date_col] ] y = media_data[target_col] media_data.drop([date_col], axis=1, inplace=True) media_data.reset_index(drop=True, inplace=True) columns = st.columns(2) old_shape = media_data.shape if "old_shape" not in st.session_state: st.session_state["old_shape"] = old_shape if "media_data" not in st.session_state: st.session_state["media_data"] = pd.DataFrame() # Sprint3 if "orig_media_data" not in st.session_state: st.session_state["orig_media_data"] = pd.DataFrame() # Sprint3 additions if "random_effects" not in st.session_state: st.session_state["random_effects"] = pd.DataFrame() if "pred_train" not in st.session_state: st.session_state["pred_train"] = [] if "pred_test" not in st.session_state: st.session_state["pred_test"] = [] # end of Sprint3 additions # Section 3 - Create combinations # bucket=['paid_search', 'kwai','indicacao','infleux', 'influencer','FB: Level Achieved - Tier 1 Impressions', # ' FB: Level Achieved - Tier 2 Impressions','paid_social_others', # ' GA App: Will And Cid Pequena Baixo Risco Clicks', # 'digital_tactic_others',"programmatic" # ] # srishti - bucket names changed bucket = [ "paid_search", "kwai", "indicacao", "infleux", "influencer", "fb_level_achieved_tier_2", "fb_level_achieved_tier_1", "paid_social_others", "ga_app", "digital_tactic_others", "programmatic", ] # with columns[0]: # if st.button('Create Combinations of Variables'): top_3_correlated_features = [] # # for col in st.session_state['media_data'].columns[:19]: # original_cols = [c for c in st.session_state['media_data'].columns if # "_clicks" in c.lower() or "_impressions" in c.lower()] # original_cols = [c for c in original_cols if "_lag" not in c.lower() and "_adstock" not in c.lower()] original_cols = ( st.session_state["bin_dict"]["Media"] + st.session_state["bin_dict"]["Internal"] ) original_cols = [ col.lower() .replace(".", "_") .replace("@", "_") .replace(" ", "_") .replace("-", "") .replace(":", "") .replace("__", "_") for col in original_cols ] original_cols = [col for col in original_cols if "_cost" not in col] # for col in st.session_state['media_data'].columns[:19]: for col in original_cols: # srishti - new corr_df = ( pd.concat( [st.session_state["media_data"].filter(regex=col), y], axis=1 ) .corr()[target_col] .iloc[:-1] ) top_3_correlated_features.append( list(corr_df.sort_values(ascending=False).head(2).index) ) flattened_list = [ item for sublist in top_3_correlated_features for item in sublist ] # all_features_set={var:[col for col in flattened_list if var in col] for var in bucket} all_features_set = { var: [col for col in flattened_list if var in col] for var in bucket if len([col for col in flattened_list if var in col]) > 0 } # srishti channels_all = [values for values in all_features_set.values()] st.session_state["combinations"] = list(itertools.product(*channels_all)) # if 'combinations' not in st.session_state: # st.session_state['combinations']=combinations_all st.session_state["final_selection"] = st.session_state["combinations"] # st.success('Created combinations') # revenue.reset_index(drop=True,inplace=True) y.reset_index(drop=True, inplace=True) if "Model_results" not in st.session_state: st.session_state["Model_results"] = { "Model_object": [], "Model_iteration": [], "Feature_set": [], "MAPE": [], "R2": [], "ADJR2": [], "pos_count": [], } def reset_model_result_dct(): st.session_state["Model_results"] = { "Model_object": [], "Model_iteration": [], "Feature_set": [], "MAPE": [], "R2": [], "ADJR2": [], "pos_count": [], } # if st.button('Build Model'): if "iterations" not in st.session_state: st.session_state["iterations"] = 0 if "final_selection" not in st.session_state: st.session_state["final_selection"] = False save_path = r"Model/" if st.session_state["final_selection"]: st.write( f'Total combinations created {format_numbers(len(st.session_state["final_selection"]))}' ) # st.session_state["project_dct"]["model_build"]["all_iters_check"] = False checkbox_default = ( st.session_state["project_dct"]["model_build"]["all_iters_check"] if st.session_state["project_dct"]["model_build"]["all_iters_check"] is not None else False ) end_date = test_start - timedelta(days=1) disp_str = "Data Split -- Training Period: " + min_date.strftime("%B %d, %Y") + " - " + end_date.strftime("%B %d, %Y") +", Testing Period: " + test_start.strftime("%B %d, %Y") + " - " + max_date.strftime("%B %d, %Y") st.markdown(disp_str) if st.checkbox("Build all iterations", value=checkbox_default): # st.session_state["project_dct"]["model_build"]["all_iters_check"] iterations = len(st.session_state["final_selection"]) st.session_state["project_dct"]["model_build"][ "all_iters_check" ] = True else: iterations = st.number_input( "Select the number of iterations to perform", min_value=0, step=100, value=st.session_state["iterations"], on_change=reset_model_result_dct, ) st.session_state["project_dct"]["model_build"][ "all_iters_check" ] = False st.session_state["project_dct"]["model_build"][ "iterations" ] = iterations # st.stop() # build_button = st.session_state["project_dct"]["model_build"]["build_button"] if \ # "build_button" in st.session_state["project_dct"]["model_build"].keys() else False # model_button =st.button('Build Model', on_click=reset_model_result_dct, key='model_build_button') # if # if model_button: if st.button( "Build Model", on_click=reset_model_result_dct, key="model_build_button", ): if iterations < 1: st.error("Please select number of iterations") st.stop() st.session_state["project_dct"]["model_build"]["build_button"] = True st.session_state["iterations"] = iterations # Section 4 - Model # st.session_state['media_data'] = st.session_state['media_data'].fillna(method='ffill') st.session_state["media_data"] = st.session_state["media_data"].ffill() progress_bar = st.progress(0) # Initialize the progress bar # time_remaining_text = st.empty() # Create an empty space for time remaining text start_time = time.time() # Record the start time progress_text = st.empty() # time_elapsed_text = st.empty() # for i, selected_features in enumerate(st.session_state["final_selection"][40000:40000 + int(iterations)]): # for i, selected_features in enumerate(st.session_state["final_selection"]): if is_panel == True: for i, selected_features in enumerate( st.session_state["final_selection"][0 : int(iterations)] ): # srishti df = st.session_state["media_data"] fet = [var for var in selected_features if len(var) > 0] inp_vars_str = " + ".join(fet) # new X = df[fet] y = df[target_col] ss = MinMaxScaler() X = pd.DataFrame(ss.fit_transform(X), columns=X.columns) X[target_col] = y # Sprint2 X[panel_col] = df[panel_col] # Sprint2 X_train = X.iloc[:train_idx] X_test = X.iloc[train_idx:] y_train = y.iloc[:train_idx] y_test = y.iloc[train_idx:] print(X_train.shape) # model = sm.OLS(y_train, X_train).fit() md_str = target_col + " ~ " + inp_vars_str # md = smf.mixedlm("total_approved_accounts_revenue ~ {}".format(inp_vars_str), # data=X_train[[target_col] + fet], # groups=X_train[panel_col]) md = smf.mixedlm( md_str, data=X_train[[target_col] + fet], groups=X_train[panel_col], ) mdf = md.fit() predicted_values = mdf.fittedvalues coefficients = mdf.fe_params.to_dict() model_positive = [ col for col in coefficients.keys() if coefficients[col] > 0 ] pvalues = [var for var in list(mdf.pvalues) if var <= 0.06] if (len(model_positive) / len(selected_features)) > 0 and ( len(pvalues) / len(selected_features) ) >= 0: # srishti - changed just for testing, revert later # predicted_values = model.predict(X_train) mape = mean_absolute_percentage_error( y_train, predicted_values ) r2 = r2_score(y_train, predicted_values) adjr2 = 1 - (1 - r2) * (len(y_train) - 1) / ( len(y_train) - len(selected_features) - 1 ) filename = os.path.join(save_path, f"model_{i}.pkl") with open(filename, "wb") as f: pickle.dump(mdf, f) # with open(r"C:\Users\ManojP\Documents\MMM\simopt\Model\model.pkl", 'rb') as file: # model = pickle.load(file) st.session_state["Model_results"]["Model_object"].append( filename ) st.session_state["Model_results"][ "Model_iteration" ].append(i) st.session_state["Model_results"]["Feature_set"].append( fet ) st.session_state["Model_results"]["MAPE"].append(mape) st.session_state["Model_results"]["R2"].append(r2) st.session_state["Model_results"]["pos_count"].append( len(model_positive) ) st.session_state["Model_results"]["ADJR2"].append(adjr2) current_time = time.time() time_taken = current_time - start_time time_elapsed_minutes = time_taken / 60 completed_iterations_text = f"{i + 1}/{iterations}" progress_bar.progress((i + 1) / int(iterations)) progress_text.text( f"Completed iterations: {completed_iterations_text},Time Elapsed (min): {time_elapsed_minutes:.2f}" ) st.write( f'Out of {st.session_state["iterations"]} iterations : {len(st.session_state["Model_results"]["Model_object"])} valid models' ) else: for i, selected_features in enumerate( st.session_state["final_selection"][0 : int(iterations)] ): # srishti df = st.session_state["media_data"] fet = [var for var in selected_features if len(var) > 0] inp_vars_str = " + ".join(fet) X = df[fet] y = df[target_col] ss = MinMaxScaler() X = pd.DataFrame(ss.fit_transform(X), columns=X.columns) X = sm.add_constant(X) X_train = X.iloc[:130] X_test = X.iloc[130:] y_train = y.iloc[:130] y_test = y.iloc[130:] model = sm.OLS(y_train, X_train).fit() coefficients = model.params.to_list() model_positive = [coef for coef in coefficients if coef > 0] predicted_values = model.predict(X_train) pvalues = [var for var in list(model.pvalues) if var <= 0.06] # if (len(model_possitive) / len(selected_features)) > 0.9 and (len(pvalues) / len(selected_features)) >= 0.8: if (len(model_positive) / len(selected_features)) > 0 and ( len(pvalues) / len(selected_features) ) >= 0.5: # srishti - changed just for testing, revert later VALID MODEL CRITERIA # predicted_values = model.predict(X_train) mape = mean_absolute_percentage_error( y_train, predicted_values ) adjr2 = model.rsquared_adj r2 = model.rsquared filename = os.path.join(save_path, f"model_{i}.pkl") with open(filename, "wb") as f: pickle.dump(model, f) # with open(r"C:\Users\ManojP\Documents\MMM\simopt\Model\model.pkl", 'rb') as file: # model = pickle.load(file) st.session_state["Model_results"]["Model_object"].append( filename ) st.session_state["Model_results"][ "Model_iteration" ].append(i) st.session_state["Model_results"]["Feature_set"].append( fet ) st.session_state["Model_results"]["MAPE"].append(mape) st.session_state["Model_results"]["R2"].append(r2) st.session_state["Model_results"]["ADJR2"].append(adjr2) st.session_state["Model_results"]["pos_count"].append( len(model_positive) ) current_time = time.time() time_taken = current_time - start_time time_elapsed_minutes = time_taken / 60 completed_iterations_text = f"{i + 1}/{iterations}" progress_bar.progress((i + 1) / int(iterations)) progress_text.text( f"Completed iterations: {completed_iterations_text},Time Elapsed (min): {time_elapsed_minutes:.2f}" ) st.write( f'Out of {st.session_state["iterations"]} iterations : {len(st.session_state["Model_results"]["Model_object"])} valid models' ) pd.DataFrame(st.session_state["Model_results"]).to_csv( "model_output.csv" ) def to_percentage(value): return f"{value * 100:.1f}%" ## Section 5 - Select Model st.title("2. Select Models") show_results_defualt = ( st.session_state["project_dct"]["model_build"]["show_results_check"] if st.session_state["project_dct"]["model_build"]["show_results_check"] is not None else False ) if "tick" not in st.session_state: st.session_state["tick"] = False if st.checkbox( "Show results of top 10 models (based on MAPE and Adj. R2)", value=True, ): st.session_state["project_dct"]["model_build"][ "show_results_check" ] = True st.session_state["tick"] = True st.write( "Select one model iteration to generate performance metrics for it:" ) data = pd.DataFrame(st.session_state["Model_results"]) data = data[data["pos_count"] == data["pos_count"].max()].reset_index( drop=True ) # Sprint4 -- Srishti -- only show models with the lowest num of neg coeffs data.sort_values(by=["ADJR2"], ascending=False, inplace=True) data.drop_duplicates(subset="Model_iteration", inplace=True) top_10 = data.head(10) top_10["Rank"] = np.arange(1, len(top_10) + 1, 1) top_10[["MAPE", "R2", "ADJR2"]] = np.round( top_10[["MAPE", "R2", "ADJR2"]], 4 ).applymap(to_percentage) top_10_table = top_10[ ["Rank", "Model_iteration", "MAPE", "ADJR2", "R2"] ] # top_10_table.columns=[['Rank','Model Iteration Index','MAPE','Adjusted R2','R2']] gd = GridOptionsBuilder.from_dataframe(top_10_table) gd.configure_pagination(enabled=True) gd.configure_selection( use_checkbox=True, selection_mode="single", pre_select_all_rows=False, pre_selected_rows=[1], ) gridoptions = gd.build() table = AgGrid( top_10, gridOptions=gridoptions, update_mode=GridUpdateMode.SELECTION_CHANGED, ) selected_rows = table.selected_rows # if st.session_state["selected_rows"] != selected_rows: # st.session_state["build_rc_cb"] = False st.session_state["selected_rows"] = selected_rows # st.write( # """ # ### Filter Results # Use the filters below to refine the displayed model results. This helps in isolating models that do not meet the required business criteria, ensuring only the most relevant models are considered for further analysis. If multiple models meet the criteria, select the first model, as it is considered the best-ranked based on evaluation criteria. # """ # ) # data = pd.DataFrame(st.session_state["Model_results"]) # coefficients_df, data_df = prepare_data_df(data) # # Define the structure of the empty DataFrame # filter_df_data = { # "Channel Name": pd.Series([], dtype="str"), # "Filter Condition": pd.Series([], dtype="str"), # "Percent Contribution": pd.Series([], dtype="str"), # } # filter_df = pd.DataFrame(filter_df_data) # filter_df_editable = st.data_editor( # filter_df, # column_config={ # "Channel Name": st.column_config.SelectboxColumn( # options=list(coefficients_df.columns), # required=True, # default="Base Sales", # ), # "Filter Condition": st.column_config.SelectboxColumn( # options=[ # "<", # ">", # "=", # "<=", # ">=", # ], # required=True, # default=">", # ), # "Percent Contribution": st.column_config.NumberColumn( # required=True, default=0 # ), # }, # hide_index=True, # use_container_width=True, # num_rows="dynamic", # ) # # Apply filters from filter_df_editable to data_df # if "filtered_df" not in st.session_state: # st.session_state["filtered_df"] = data_df.copy() # if st.button("Filter", args=(data_df)): # st.session_state["filtered_df"] = data_df.copy() # for index, row in filter_df_editable.iterrows(): # channel_name = row["Channel Name"] # condition = row["Filter Condition"] # value = row["Percent Contribution"] # if channel_name in st.session_state["filtered_df"].columns: # # Construct the query string based on the condition # query_string = f"`{channel_name}` {condition} {value}" # st.session_state["filtered_df"] = st.session_state["filtered_df"].query( # query_string # ) # # After filtering, check if the DataFrame is empty # if st.session_state["filtered_df"].empty: # # Display a warning message if no rows meet the filter criteria # st.warning("No model meets the specified filter conditions", icon="⚠️") # st.stop() # Optionally stop further execution # # Output the filtered data # st.write("Select one model iteration to generate performance metrics for it:") # st.dataframe(st.session_state["filtered_df"], hide_index=True) ############################################################################################# # top_10 = data.head(10) # top_10["Rank"] = np.arange(1, len(top_10) + 1, 1) # top_10[["MAPE", "R2", "ADJR2"]] = np.round( # top_10[["MAPE", "R2", "ADJR2"]], 4 # ).applymap(to_percentage) # top_10_table = top_10[ # ["Rank", "Model_iteration", "MAPE", "ADJR2", "R2"] # + list(coefficients_df.columns) # ] # top_10_table.columns=[['Rank','Model Iteration Index','MAPE','Adjusted R2','R2']] # gd = GridOptionsBuilder.from_dataframe(top_10_table) # gd.configure_pagination(enabled=True) # gd.configure_selection( # use_checkbox=True, # selection_mode="single", # pre_select_all_rows=False, # pre_selected_rows=[1], # ) # gridoptions = gd.build() # table = AgGrid( # top_10, gridOptions=gridoptions, update_mode=GridUpdateMode.SELECTION_CHANGED # ) # selected_rows = table.selected_rows # gd = GridOptionsBuilder.from_dataframe(st.session_state["filtered_df"]) # gd.configure_pagination(enabled=True) # gd.configure_selection( # use_checkbox=True, # selection_mode="single", # pre_select_all_rows=False, # pre_selected_rows=[1], # ) # gridoptions = gd.build() # table = AgGrid( # st.session_state["filtered_df"], # gridOptions=gridoptions, # update_mode=GridUpdateMode.SELECTION_CHANGED, # ) # selected_rows_table = table.selected_rows # Dataframe # display_df = st.session_state.filtered_df.rename(columns={"Rank": "Model Number"}) # st.dataframe(display_df, hide_index=True) # min_rank = min(st.session_state["filtered_df"]["Rank"]) # max_rank = max(st.session_state["filtered_df"]["Rank"]) # available_ranks = st.session_state["filtered_df"]["Rank"].unique() # # Get row number input from the user # rank_number = st.number_input( # "Select model by Model Number:", # min_value=min_rank, # max_value=max_rank, # value=min_rank, # step=1, # ) # # Get row # if rank_number not in available_ranks: # st.warning("No model is available with selected Rank", icon="⚠️") # st.stop() # Find the row that matches the selected rank # selected_rows = st.session_state["filtered_df"][ # st.session_state["filtered_df"]["Rank"] == rank_number # ] # selected_rows = [ # (selected_rows.to_dict(orient="records")[0] if not selected_rows.empty else {}) # ] # if st.session_state["selected_rows"] != selected_rows: # st.session_state["build_rc_cb"] = False st.session_state["selected_rows"] = selected_rows if "Model" not in st.session_state: st.session_state["Model"] = {} # Section 6 - Display Results # Section 6 - Display Results if len(selected_rows) > 0: st.header("2.1 Results Summary") model_object = data[ data["Model_iteration"] == selected_rows[0]["Model_iteration"] ]["Model_object"] features_set = data[ data["Model_iteration"] == selected_rows[0]["Model_iteration"] ]["Feature_set"] with open(str(model_object.values[0]), "rb") as file: # print(file) model = pickle.load(file) st.write(model.summary()) st.header("2.2 Actual vs. Predicted Plot") if is_panel: df = st.session_state["media_data"] X = df[features_set.values[0]] y = df[target_col] ss = MinMaxScaler() X = pd.DataFrame(ss.fit_transform(X), columns=X.columns) # Sprint2 changes X[target_col] = y # new X[panel_col] = df[panel_col] X[date_col] = date X_train = X.iloc[:train_idx] X_test = X.iloc[train_idx:].reset_index(drop=True) y_train = y.iloc[:train_idx] y_test = y.iloc[train_idx:].reset_index(drop=True) test_spends = spends_data[ train_idx: ] # Sprint3 - test spends for resp curves random_eff_df = get_random_effects( media_data, panel_col, model ) train_pred = model.fittedvalues test_pred = mdf_predict(X_test, model, random_eff_df) print("__" * 20, test_pred.isna().sum()) else: df = st.session_state["media_data"] X = df[features_set.values[0]] y = df[target_col] ss = MinMaxScaler() X = pd.DataFrame(ss.fit_transform(X), columns=X.columns) X = sm.add_constant(X) X[date_col] = date X_train = X.iloc[:130] X_test = X.iloc[130:].reset_index(drop=True) y_train = y.iloc[:130] y_test = y.iloc[130:].reset_index(drop=True) test_spends = spends_data[ 130: ] # Sprint3 - test spends for resp curves train_pred = model.predict( X_train[features_set.values[0] + ["const"]] ) test_pred = model.predict( X_test[features_set.values[0] + ["const"]] ) # save x test to test - srishti # x_test_to_save = X_test.copy() # x_test_to_save['Actuals'] = y_test # x_test_to_save['Predictions'] = test_pred # # x_train_to_save = X_train.copy() # x_train_to_save['Actuals'] = y_train # x_train_to_save['Predictions'] = train_pred # # x_train_to_save.to_csv('Test/x_train_to_save.csv', index=False) # x_test_to_save.to_csv('Test/x_test_to_save.csv', index=False) st.session_state["X"] = X_train st.session_state["features_set"] = features_set.values[0] print( "**" * 20, "selected model features : ", features_set.values[0] ) metrics_table, line, actual_vs_predicted_plot = ( plot_actual_vs_predicted( X_train[date_col], y_train, train_pred, model, target_column=sel_target_col, is_panel=is_panel, ) ) # Sprint2 st.plotly_chart(actual_vs_predicted_plot, use_container_width=True) st.markdown("## 2.3 Residual Analysis") columns = st.columns(2) with columns[0]: fig = plot_residual_predicted( y_train, train_pred, X_train ) # Sprint2 st.plotly_chart(fig) with columns[1]: st.empty() fig = qqplot(y_train, train_pred) # Sprint2 st.plotly_chart(fig) with columns[0]: fig = residual_distribution(y_train, train_pred) # Sprint2 st.pyplot(fig) vif_data = pd.DataFrame() # X=X.drop('const',axis=1) X_train_orig = ( X_train.copy() ) # Sprint2 -- creating a copy of xtrain. Later deleting panel, target & date from xtrain del_col_list = list( set([target_col, panel_col, date_col]).intersection( set(X_train.columns) ) ) X_train.drop(columns=del_col_list, inplace=True) # Sprint2 vif_data["Variable"] = X_train.columns vif_data["VIF"] = [ variance_inflation_factor(X_train.values, i) for i in range(X_train.shape[1]) ] vif_data.sort_values(by=["VIF"], ascending=False, inplace=True) vif_data = np.round(vif_data) vif_data["VIF"] = vif_data["VIF"].astype(float) st.header("2.4 Variance Inflation Factor (VIF)") # st.dataframe(vif_data) color_mapping = { "darkgreen": (vif_data["VIF"] < 3), "orange": (vif_data["VIF"] >= 3) & (vif_data["VIF"] <= 10), "darkred": (vif_data["VIF"] > 10), } # Create a horizontal bar plot fig, ax = plt.subplots() fig.set_figwidth(10) # Adjust the width of the figure as needed # Sort the bars by descending VIF values vif_data = vif_data.sort_values(by="VIF", ascending=False) # Iterate through the color mapping and plot bars with corresponding colors for color, condition in color_mapping.items(): subset = vif_data[condition] bars = ax.barh( subset["Variable"], subset["VIF"], color=color, label=color ) # Add text annotations on top of the bars for bar in bars: width = bar.get_width() ax.annotate( f"{width:}", xy=(width, bar.get_y() + bar.get_height() / 2), xytext=(5, 0), textcoords="offset points", va="center", ) # Customize the plot ax.set_xlabel("VIF Values") # ax.set_title('2.4 Variance Inflation Factor (VIF)') # ax.legend(loc='upper right') # Display the plot in Streamlit st.pyplot(fig) with st.expander("Results Summary Test data"): # ss = MinMaxScaler() # X_test = pd.DataFrame(ss.fit_transform(X_test), columns=X_test.columns) st.header("2.2 Actual vs. Predicted Plot") metrics_table, line, actual_vs_predicted_plot = ( plot_actual_vs_predicted( X_test[date_col], y_test, test_pred, model, target_column=sel_target_col, is_panel=is_panel, ) ) # Sprint2 st.plotly_chart( actual_vs_predicted_plot, use_container_width=True ) st.markdown("## 2.3 Residual Analysis") columns = st.columns(2) with columns[0]: fig = plot_residual_predicted( y, test_pred, X_test ) # Sprint2 st.plotly_chart(fig) with columns[1]: st.empty() fig = qqplot(y, test_pred) # Sprint2 st.plotly_chart(fig) with columns[0]: fig = residual_distribution(y, test_pred) # Sprint2 st.pyplot(fig) value = False save_button_model = st.checkbox( "Save this model to tune", key="build_rc_cb" ) # , on_click=set_save()) if save_button_model: mod_name = st.text_input("Enter model name") if len(mod_name) > 0: mod_name = ( mod_name + "__" + target_col ) # Sprint4 - adding target col to model name if is_panel: pred_train = model.fittedvalues pred_test = mdf_predict(X_test, model, random_eff_df) else: st.session_state["features_set"] = st.session_state[ "features_set" ] + ["const"] pred_train = model.predict( X_train_orig[st.session_state["features_set"]] ) pred_test = model.predict( X_test[st.session_state["features_set"]] ) st.session_state["Model"][mod_name] = { "Model_object": model, "feature_set": st.session_state["features_set"], "X_train": X_train_orig, "X_test": X_test, "y_train": y_train, "y_test": y_test, "pred_train": pred_train, "pred_test": pred_test, } st.session_state["X_train"] = X_train_orig st.session_state["X_test_spends"] = test_spends st.session_state["saved_model_names"].append(mod_name) # Sprint3 additions if is_panel: random_eff_df = get_random_effects( media_data, panel_col, model ) st.session_state["random_effects"] = random_eff_df with open( os.path.join( st.session_state["project_path"], "best_models.pkl" ), "wb", ) as f: pickle.dump(st.session_state["Model"], f) st.success( mod_name + " model saved! Proceed to the next page to tune the model" ) urm = st.session_state["used_response_metrics"] urm.append(sel_target_col) st.session_state["used_response_metrics"] = list( set(urm) ) mod_name = "" # Sprint4 - add the formatted name of the target col to used resp metrics value = False st.session_state["project_dct"]["model_build"][ "session_state_saved" ] = {} for key in [ "Model", "bin_dict", "used_response_metrics", "date", "saved_model_names", "media_data", "X_test_spends", ]: st.session_state["project_dct"]["model_build"][ "session_state_saved" ][key] = st.session_state[key] project_dct_path = os.path.join( st.session_state["project_path"], "project_dct.pkl" ) with open(project_dct_path, "wb") as f: pickle.dump(st.session_state["project_dct"], f) update_db("4_Model_Build.py") st.toast("💾 Saved Successfully!") else: st.session_state["project_dct"]["model_build"][ "show_results_check" ] = False