Spaces:
Sleeping
Sleeping
File size: 25,862 Bytes
bd80083 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 |
'''
MMO Build Sprint 3
date :
changes : capability to tune MixedLM as well as simple LR in the same page
'''
import streamlit as st
import pandas as pd
from Eda_functions import format_numbers
import pickle
from utilities import set_header, load_local_css
import statsmodels.api as sm
import re
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
from statsmodels.stats.outliers_influence import variance_inflation_factor
st.set_option('deprecation.showPyplotGlobalUse', False)
import statsmodels.formula.api as smf
from Data_prep_functions import *
# for i in ["model_tuned", "X_train_tuned", "X_test_tuned", "tuned_model_features", "tuned_model", "tuned_model_dict"] :
st.set_page_config(
page_title="Model Tuning",
page_icon=":shark:",
layout="wide",
initial_sidebar_state='collapsed'
)
load_local_css('styles.css')
set_header()
# Sprint3
# is_panel = st.session_state['is_panel']
# panel_col = 'markets' # set the panel column
date_col = 'date'
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
# flag indicating there is not tuned model till now
# Sprint4 - model tuned dict
if 'Model_Tuned' not in st.session_state:
st.session_state['Model_Tuned'] = {}
st.title('1. Model Tuning')
# st.write(st.session_state['base_model_feature_set'])
if "X_train" not in st.session_state:
st.error(
"Oops! It seems there are no saved models available. Please build and save a model from the previous page to proceed.")
st.stop()
# X_train=st.session_state['X_train']
# X_test=st.session_state['X_test']
# y_train=st.session_state['y_train']
# y_test=st.session_state['y_test']
# df=st.session_state['media_data']
# st.write(X_train.columns)
# st.write(X_test.columns)
if "is_tuned_model" not in st.session_state:
st.session_state["is_tuned_model"] = {}
# Sprint4 - if used_response_metrics is not blank, then select one of the used_response_metrics, else target is revenue by default
if "used_response_metrics" in st.session_state and st.session_state['used_response_metrics'] != []:
sel_target_col = st.selectbox("Select the response metric", st.session_state['used_response_metrics'])
target_col = sel_target_col.lower().replace(" ", "_").replace('-', '').replace(':', '').replace("__", "_")
else:
sel_target_col = 'Total Approved Accounts - Revenue'
target_col = 'total_approved_accounts_revenue'
# Sprint4 - Look through all saved models, only show saved models of the sel resp metric (target_col)
saved_models = st.session_state['saved_model_names']
required_saved_models = [m.split("__")[0] for m in saved_models if m.split("__")[1] == target_col]
sel_model = st.selectbox("Select the model to tune", required_saved_models)
with open("best_models.pkl", 'rb') as file:
model_dict = pickle.load(file)
sel_model_dict = model_dict[sel_model + "__" + target_col] # Sprint4 - get the model obj of the selected model
# st.write(sel_model_dict)
X_train = sel_model_dict['X_train']
X_test = sel_model_dict['X_test']
y_train = sel_model_dict['y_train']
y_test = sel_model_dict['y_test']
df = st.session_state['media_data']
if 'selected_model' not in st.session_state:
st.session_state['selected_model'] = 0
# st.write(model_dict[st.session_state["selected_model"]]['X_train'].columns)
st.markdown('### 1.1 Event Flags')
st.markdown('Helps in quantifying the impact of specific occurrences of events')
with st.expander('Apply Event Flags'):
# st.session_state["selected_model"]=st.selectbox('Select Model to apply flags',model_dict.keys())
model = sel_model_dict['Model_object']
date = st.session_state['date']
date = pd.to_datetime(date)
X_train = sel_model_dict['X_train']
# features_set= model_dict[st.session_state["selected_model"]]['feature_set']
features_set = sel_model_dict["feature_set"]
col = st.columns(3)
min_date = min(date)
max_date = max(date)
with col[0]:
start_date = st.date_input('Select Start Date', min_date, min_value=min_date, max_value=max_date)
with col[1]:
end_date = st.date_input('Select End Date', max_date, min_value=min_date, max_value=max_date)
with col[2]:
repeat = st.selectbox('Repeat Annually', ['Yes', 'No'], index=1)
if repeat == 'Yes':
repeat = True
else:
repeat = False
if 'Flags' not in st.session_state:
st.session_state['Flags'] = {}
# print("**"*50)
# print(y_train)
# print("**"*50)
# print(model.fittedvalues)
if is_panel: # Sprint3
met, line_values, fig_flag = plot_actual_vs_predicted(X_train[date_col], y_train,
model.fittedvalues, model,
target_column=sel_target_col,
flag=(start_date, end_date),
repeat_all_years=repeat, is_panel=True)
st.plotly_chart(fig_flag, use_container_width=True)
# create flag on test
met, test_line_values, fig_flag = plot_actual_vs_predicted(X_test[date_col], y_test,
sel_model_dict['pred_test'], model,
target_column=sel_target_col,
flag=(start_date, end_date),
repeat_all_years=repeat, is_panel=True)
else:
pred_train=model.predict(X_train[features_set])
met, line_values, fig_flag = plot_actual_vs_predicted(X_train[date_col], y_train, pred_train, model,
flag=(start_date, end_date), repeat_all_years=repeat,is_panel=False)
st.plotly_chart(fig_flag, use_container_width=True)
pred_test=model.predict(X_test[features_set])
met, test_line_values, fig_flag = plot_actual_vs_predicted(X_test[date_col], y_test, pred_test, model,
flag=(start_date, end_date), repeat_all_years=repeat,is_panel=False)
flag_name = 'f1_flag'
flag_name = st.text_input('Enter Flag Name')
# Sprint4 - add selected target col to flag name
if st.button('Update flag'):
st.session_state['Flags'][flag_name + '__'+ target_col] = {}
st.session_state['Flags'][flag_name + '__'+ target_col]['train'] = line_values
st.session_state['Flags'][flag_name + '__'+ target_col]['test'] = test_line_values
# st.write(st.session_state['Flags'][flag_name])
st.success(f'{flag_name + "__" + target_col} stored')
# Sprint4 - only show flag created for the particular target col
st.write(st.session_state['Flags'].keys() )
target_model_flags = [f.split("__")[0] for f in st.session_state['Flags'].keys() if f.split("__")[1] == target_col]
options = list(target_model_flags)
selected_options = []
num_columns = 4
num_rows = -(-len(options) // num_columns)
tick = False
if st.checkbox('Select all'):
tick = True
selected_options = []
for row in range(num_rows):
cols = st.columns(num_columns)
for col in cols:
if options:
option = options.pop(0)
selected = col.checkbox(option, value=tick)
if selected:
selected_options.append(option)
st.markdown('### 1.2 Select Parameters to Apply')
parameters = st.columns(3)
with parameters[0]:
Trend = st.checkbox("**Trend**")
st.markdown('Helps account for long-term trends or seasonality that could influence advertising effectiveness')
with parameters[1]:
week_number = st.checkbox('**Week_number**')
st.markdown('Assists in detecting and incorporating weekly patterns or seasonality')
with parameters[2]:
sine_cosine = st.checkbox('**Sine and Cosine Waves**')
st.markdown('Helps in capturing cyclical patterns or seasonality in the data')
#
# def get_tuned_model():
# st.session_state['build_tuned_model']=True
if st.button('Build model with Selected Parameters and Flags', key='build_tuned_model'):
new_features = features_set
st.header('2.1 Results Summary')
# date=list(df.index)
# df = df.reset_index(drop=True)
# st.write(df.head(2))
# X_train=df[features_set]
ss = MinMaxScaler()
if is_panel == True:
X_train_tuned = X_train[features_set]
# X_train_tuned = pd.DataFrame(ss.fit_transform(X), columns=X.columns)
X_train_tuned[target_col] = X_train[target_col]
X_train_tuned[date_col] = X_train[date_col]
X_train_tuned[panel_col] = X_train[panel_col]
X_test_tuned = X_test[features_set]
# X_test_tuned = pd.DataFrame(ss.transform(X), columns=X.columns)
X_test_tuned[target_col] = X_test[target_col]
X_test_tuned[date_col] = X_test[date_col]
X_test_tuned[panel_col] = X_test[panel_col]
else:
X_train_tuned = X_train[features_set]
# X_train_tuned = pd.DataFrame(ss.fit_transform(X_train_tuned), columns=X_train_tuned.columns)
X_test_tuned = X_test[features_set]
# X_test_tuned = pd.DataFrame(ss.transform(X_test_tuned), columns=X_test_tuned.columns)
for flag in selected_options:
# Spirnt4 - added target_col in flag name
X_train_tuned[flag] = st.session_state['Flags'][flag + "__" + target_col]['train']
X_test_tuned[flag] = st.session_state['Flags'][flag + "__" + target_col]['test']
# test
# X_train_tuned.to_csv("Test/X_train_tuned_flag.csv",index=False)
# X_test_tuned.to_csv("Test/X_test_tuned_flag.csv",index=False)
# print("()()"*20,flag, len(st.session_state['Flags'][flag]))
if Trend:
# Sprint3 - group by panel, calculate trend of each panel spearately. Add trend to new feature set
if is_panel:
newdata = pd.DataFrame()
panel_wise_end_point_train = {}
for panel, groupdf in X_train_tuned.groupby(panel_col):
groupdf.sort_values(date_col, inplace=True)
groupdf['Trend'] = np.arange(1, len(groupdf) + 1, 1)
newdata = pd.concat([newdata, groupdf])
panel_wise_end_point_train[panel] = len(groupdf)
X_train_tuned = newdata.copy()
test_newdata = pd.DataFrame()
for panel, test_groupdf in X_test_tuned.groupby(panel_col):
test_groupdf.sort_values(date_col, inplace=True)
start = panel_wise_end_point_train[panel] + 1
end = start + len(test_groupdf) # should be + 1? - Sprint4
# print("??"*20, panel, len(test_groupdf), len(np.arange(start, end, 1)), start)
test_groupdf['Trend'] = np.arange(start, end, 1)
test_newdata = pd.concat([test_newdata, test_groupdf])
X_test_tuned = test_newdata.copy()
new_features = new_features + ['Trend']
else:
X_train_tuned['Trend'] = np.arange(1, len(X_train_tuned) + 1, 1)
X_test_tuned['Trend'] = np.arange(len(X_train_tuned) + 1, len(X_train_tuned) + len(X_test_tuned) + 1, 1)
new_features = new_features + ['Trend']
if week_number:
# Sprint3 - create weeknumber from date column in xtrain tuned. add week num to new feature set
if is_panel:
X_train_tuned[date_col] = pd.to_datetime(X_train_tuned[date_col])
X_train_tuned['Week_number'] = X_train_tuned[date_col].dt.day_of_week
if X_train_tuned['Week_number'].nunique() == 1:
st.write("All dates in the data are of the same week day. Hence Week number can't be used.")
else:
X_test_tuned[date_col] = pd.to_datetime(X_test_tuned[date_col])
X_test_tuned['Week_number'] = X_test_tuned[date_col].dt.day_of_week
new_features = new_features + ['Week_number']
else:
date = pd.to_datetime(date.values)
X_train_tuned['Week_number'] = pd.to_datetime(X_train[date_col]).dt.day_of_week
X_test_tuned['Week_number'] = pd.to_datetime(X_test[date_col]).dt.day_of_week
new_features = new_features + ['Week_number']
if sine_cosine:
# Sprint3 - create panel wise sine cosine waves in xtrain tuned. add to new feature set
if is_panel:
new_features = new_features + ['sine_wave', 'cosine_wave']
newdata = pd.DataFrame()
newdata_test = pd.DataFrame()
groups = X_train_tuned.groupby(panel_col)
frequency = 2 * np.pi / 365 # Adjust the frequency as needed
train_panel_wise_end_point = {}
for panel, groupdf in groups:
num_samples = len(groupdf)
train_panel_wise_end_point[panel] = num_samples
days_since_start = np.arange(num_samples)
sine_wave = np.sin(frequency * days_since_start)
cosine_wave = np.cos(frequency * days_since_start)
sine_cosine_df = pd.DataFrame({'sine_wave': sine_wave, 'cosine_wave': cosine_wave})
assert len(sine_cosine_df) == len(groupdf)
# groupdf = pd.concat([groupdf, sine_cosine_df], axis=1)
groupdf['sine_wave'] = sine_wave
groupdf['cosine_wave'] = cosine_wave
newdata = pd.concat([newdata, groupdf])
X_train_tuned = newdata.copy()
test_groups = X_test_tuned.groupby(panel_col)
for panel, test_groupdf in test_groups:
num_samples = len(test_groupdf)
start = train_panel_wise_end_point[panel]
days_since_start = np.arange(start, start + num_samples, 1)
# print("##", panel, num_samples, start, len(np.arange(start, start+num_samples, 1)))
sine_wave = np.sin(frequency * days_since_start)
cosine_wave = np.cos(frequency * days_since_start)
sine_cosine_df = pd.DataFrame({'sine_wave': sine_wave, 'cosine_wave': cosine_wave})
assert len(sine_cosine_df) == len(test_groupdf)
# groupdf = pd.concat([groupdf, sine_cosine_df], axis=1)
test_groupdf['sine_wave'] = sine_wave
test_groupdf['cosine_wave'] = cosine_wave
newdata_test = pd.concat([newdata_test, test_groupdf])
X_test_tuned = newdata_test.copy()
else:
new_features = new_features + ['sine_wave', 'cosine_wave']
num_samples = len(X_train_tuned)
frequency = 2 * np.pi / 365 # Adjust the frequency as needed
days_since_start = np.arange(num_samples)
sine_wave = np.sin(frequency * days_since_start)
cosine_wave = np.cos(frequency * days_since_start)
sine_cosine_df = pd.DataFrame({'sine_wave': sine_wave, 'cosine_wave': cosine_wave})
# Concatenate the sine and cosine waves with the scaled X DataFrame
X_train_tuned = pd.concat([X_train_tuned, sine_cosine_df], axis=1)
test_num_samples = len(X_test_tuned)
start = num_samples
days_since_start = np.arange(start, start + test_num_samples, 1)
sine_wave = np.sin(frequency * days_since_start)
cosine_wave = np.cos(frequency * days_since_start)
sine_cosine_df = pd.DataFrame({'sine_wave': sine_wave, 'cosine_wave': cosine_wave})
# Concatenate the sine and cosine waves with the scaled X DataFrame
X_test_tuned = pd.concat([X_test_tuned, sine_cosine_df], axis=1)
# model
if selected_options:
new_features = new_features + selected_options
if is_panel:
inp_vars_str = " + ".join(new_features)
new_features=list(set(new_features))
# X_train_tuned.to_csv("Test/X_train_tuned.csv",index=False)
# st.write(X_train_tuned[['total_approved_accounts_revenue'] + new_features].dtypes)
# st.write(X_train_tuned[['total_approved_accounts_revenue', panel_col] + new_features].isna().sum())
md_str = target_col + " ~ " + inp_vars_str
md_tuned = smf.mixedlm(md_str,
data=X_train_tuned[[target_col] + new_features],
groups=X_train_tuned[panel_col])
model_tuned = md_tuned.fit()
# plot act v pred for original model and tuned model
metrics_table, line, actual_vs_predicted_plot = plot_actual_vs_predicted(X_train[date_col], y_train,
model.fittedvalues, model,
target_column=sel_target_col,
is_panel=True)
metrics_table_tuned, line, actual_vs_predicted_plot_tuned = plot_actual_vs_predicted(X_train_tuned[date_col],
X_train_tuned[target_col],
model_tuned.fittedvalues,
model_tuned,
target_column=sel_target_col,
is_panel=True)
else:
new_features=list(set(new_features))
# st.write(new_features)
model_tuned = sm.OLS(y_train, X_train_tuned[new_features]).fit()
# st.write(X_train_tuned.columns)
metrics_table, line, actual_vs_predicted_plot = plot_actual_vs_predicted(date[:130], y_train,
model.predict(X_train[features_set]), model,
target_column=sel_target_col)
metrics_table_tuned, line, actual_vs_predicted_plot_tuned = plot_actual_vs_predicted(date[:130], y_train,
model_tuned.predict(
X_train_tuned),
model_tuned,
target_column=sel_target_col)
# st.write(metrics_table_tuned)
mape = np.round(metrics_table.iloc[0, 1], 2)
r2 = np.round(metrics_table.iloc[1, 1], 2)
adjr2 = np.round(metrics_table.iloc[2, 1], 2)
mape_tuned = np.round(metrics_table_tuned.iloc[0, 1], 2)
r2_tuned = np.round(metrics_table_tuned.iloc[1, 1], 2)
adjr2_tuned = np.round(metrics_table_tuned.iloc[2, 1], 2)
parameters_ = st.columns(3)
with parameters_[0]:
st.metric('R2', r2_tuned, np.round(r2_tuned - r2, 2))
with parameters_[1]:
st.metric('Adjusted R2', adjr2_tuned, np.round(adjr2_tuned - adjr2, 2))
with parameters_[2]:
st.metric('MAPE', mape_tuned, np.round(mape_tuned - mape, 2), 'inverse')
st.write(model_tuned.summary())
X_train_tuned[date_col] = X_train[date_col]
X_test_tuned[date_col] = X_test[date_col]
X_train_tuned[target_col] = y_train
X_test_tuned[target_col] = y_test
st.header('2.2 Actual vs. Predicted Plot')
# if is_panel:
# metrics_table, line, actual_vs_predicted_plot = plot_actual_vs_predicted(date, y_train, model.predict(X_train),
# model, target_column='Revenue',is_panel=True)
# else:
# metrics_table,line,actual_vs_predicted_plot=plot_actual_vs_predicted(date, y_train, model.predict(X_train), model,target_column='Revenue')
if is_panel :
metrics_table, line, actual_vs_predicted_plot = plot_actual_vs_predicted(X_train_tuned[date_col],
X_train_tuned[target_col],
model_tuned.fittedvalues, model_tuned,
target_column=sel_target_col,
is_panel=True)
else :
metrics_table, line, actual_vs_predicted_plot = plot_actual_vs_predicted(X_train_tuned[date_col],
X_train_tuned[target_col],
model_tuned.predict(X_train_tuned[new_features]),
model_tuned,
target_column=sel_target_col,
is_panel=False)
# plot_actual_vs_predicted(X_train[date_col], y_train,
# model.fittedvalues, model,
# target_column='Revenue',
# is_panel=is_panel)
st.plotly_chart(actual_vs_predicted_plot, use_container_width=True)
st.markdown('## 2.3 Residual Analysis')
if is_panel :
columns = st.columns(2)
with columns[0]:
fig = plot_residual_predicted(y_train, model_tuned.fittedvalues, X_train_tuned)
st.plotly_chart(fig)
with columns[1]:
st.empty()
fig = qqplot(y_train, model_tuned.fittedvalues)
st.plotly_chart(fig)
with columns[0]:
fig = residual_distribution(y_train, model_tuned.fittedvalues)
st.pyplot(fig)
else:
columns = st.columns(2)
with columns[0]:
fig = plot_residual_predicted(y_train, model_tuned.predict(X_train_tuned[new_features]), X_train)
st.plotly_chart(fig)
with columns[1]:
st.empty()
fig = qqplot(y_train, model_tuned.predict(X_train_tuned[new_features]))
st.plotly_chart(fig)
with columns[0]:
fig = residual_distribution(y_train, model_tuned.predict(X_train_tuned[new_features]))
st.pyplot(fig)
st.session_state['is_tuned_model'][target_col] = True
# Sprint4 - saved tuned model in a dict
st.session_state['Model_Tuned'][sel_model + "__" + target_col] = {
"Model_object": model_tuned,
'feature_set': new_features,
'X_train_tuned': X_train_tuned,
'X_test_tuned': X_test_tuned
}
# Pending
# if st.session_state['build_tuned_model']==True:
if st.session_state['Model_Tuned'] is not None :
if st.checkbox('Use this model to build response curves', key='save_model'):
# save_model = st.button('Use this model to build response curves', key='saved_tuned_model')
# if save_model:
st.session_state["is_tuned_model"][target_col]=True
with open("tuned_model.pkl", "wb") as f:
# pickle.dump(st.session_state['tuned_model'], f)
pickle.dump(st.session_state['Model_Tuned'], f) # Sprint4
# X_test_tuned.to_csv("Test/X_test_tuned_final.csv", index=False)
# X_train_tuned.to_csv("Test/X_train_tuned.csv", index=False)
st.success(sel_model + "__" + target_col + ' Tuned saved!')
# if is_panel:
# # st.session_state["tuned_model_features"] = new_features
# with open("tuned_model.pkl", "wb") as f:
# # pickle.dump(st.session_state['tuned_model'], f)
# pickle.dump(st.session_state['Model_Tuned'], f) # Sprint4
# st.success(sel_model + "__" + target_col + ' Tuned saved!')
# raw_data=df[features_set]
# columns_raw=[re.split(r"(_lag|_adst)",col)[0] for col in raw_data.columns]
# raw_data.columns=columns_raw
# columns_media=[col for col in columns_raw if Categorised_data[col]['BB']=='Media']
# raw_data=raw_data[columns_media]
# raw_data['Date']=list(df.index)
# spends_var=[col for col in df.columns if "spends" in col.lower() and 'adst' not in col.lower() and 'lag' not in col.lower()]
# spends_df=df[spends_var]
# spends_df['Week']=list(df.index)
# j=0
# X1=X.copy()
# col=X1.columns
# for i in model.params.values:
# X1[col[j]]=X1.iloc[:,j]*i
# j+=1
# contribution_df=X1
# contribution_df['Date']=list(df.index)
# excel_file='Overview_data.xlsx'
# with pd.ExcelWriter(excel_file,engine='xlsxwriter') as writer:
# raw_data.to_excel(writer,sheet_name='RAW DATA MMM',index=False)
# spends_df.to_excel(writer,sheet_name='SPEND INPUT',index=False)
# contribution_df.to_excel(writer,sheet_name='CONTRIBUTION MMM')
|