File size: 25,893 Bytes
e4e60c1 7a4444d e4e60c1 eb75667 e4e60c1 a734b5e e4e60c1 0a3df69 e4e60c1 a734b5e e4e60c1 2bd7f02 e4e60c1 7a4444d e4e60c1 eb75667 e4e60c1 a734b5e e4e60c1 0a3df69 e4e60c1 a734b5e e4e60c1 7a4444d e4e60c1 eb75667 e4e60c1 b3e6023 e4e60c1 75eb0c5 e4e60c1 6201f7a e4e60c1 13984a2 e4e60c1 6201f7a e4e60c1 0356a8c e4e60c1 75eb0c5 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 |
# %%
# Import section
# (Please don't edit this section unless if necessary)
import copy
from pathlib import Path
import warnings
import holidays
import seaborn as sns
import matplotlib
import matplotlib.dates as mdates
import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')
import numpy as np
import pandas as pd
import glob
import csv
import lightning.pytorch as pl
from lightning.pytorch.callbacks import EarlyStopping, LearningRateMonitor
from lightning.pytorch.loggers import TensorBoardLogger
import torch
from pytorch_forecasting import Baseline, TemporalFusionTransformer, TimeSeriesDataSet
from pytorch_forecasting.data import GroupNormalizer, NaNLabelEncoder
from pytorch_forecasting.metrics import SMAPE, PoissonLoss, QuantileLoss
from pytorch_forecasting.models.temporal_fusion_transformer.tuning import optimize_hyperparameters
import random
import gc
import tensorflow as tf
import tensorboard as tb
tf.io.gfile = tb.compat.tensorflow_stub.io.gfile
import os
import math
import sys
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
import tensorflow as tf
from tensorflow.keras.layers import Conv1D, LSTM, Dense, Dropout, Bidirectional, TimeDistributed
from tensorflow.keras.layers import MaxPooling1D, Flatten
from tensorflow.keras.regularizers import L1, L2
from tensorflow.keras.metrics import Accuracy
from tensorflow.keras.metrics import RootMeanSquaredError
from sklearn.metrics import mean_squared_error as MSE
from sklearn.model_selection import KFold
from sklearn.inspection import permutation_importance
from tensorflow.keras.utils import plot_model
from sklearn.metrics import explained_variance_score, mean_poisson_deviance, mean_gamma_deviance, mean_squared_error, mean_squared_log_error, d2_absolute_error_score, d2_pinball_score, d2_tweedie_score
from sklearn.metrics import r2_score
from sklearn.metrics import max_error
import datetime
from datetime import date
import optuna
from tensorflow.keras.callbacks import Callback
from optuna.integration import TFKerasPruningCallback
import shutil
import gradio as gr
# Some variables (don't edit these variables unless if necessary)
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
random.seed(30)
np.random.seed(30)
tf.random.set_seed(30)
torch.manual_seed(30)
torch.cuda.manual_seed(30)
# Global variables
PATIENCE = 30
MAX_EPOCHS = 3
LEARNING_RATE = 0.01
OPTUNA = True
ACCELERATOR = "cpu"
# This below line is only for GPU. Don't use it for CPU
#os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "max_split_size_mb:1024"
# Variables to count the number of files
w = 7
prax = [0 for x in range(w)]
# %%
# Function to train the model (TFT)
def modelTFT(csv_file, prax):
train = csv_file
#test = pd.read_csv("/kaggle/input/artemis-test/nifty_daily.csv")
train['date'] = pd.to_datetime(train['Date/Time'])
#test['date'] = pd.to_datetime(test['Date'])
data = pd.concat([train], axis = 0, ignore_index=True)
# Check that key is country-store-product-date combination
#assert len(data.drop_duplicates(['country', 'store', 'product', 'date'])) == len(data)
# Check that there is one date per country-store-product combination
#assert len(data.drop_duplicates(['country', 'store', 'product'])) == len(data)//data['date'].nunique()
#display(train.sample(4))
# Add a time_idx (an sequence of consecutive integers that goes from min to max date)
data = (data.merge((data[['Date/Time']].drop_duplicates(ignore_index=True)
.rename_axis('time_idx')).reset_index(), on = ['Date/Time']))
# add additional features
data["day_of_week"] = data['date'].dt.dayofweek.astype(str).astype("category") # categories have be strings
data["week_of_year"] = data['date'].dt.isocalendar().week.astype(str).astype("category") # categories have be strings
data["month"] = data['date'].dt.month.astype(str).astype("category") # categories have be strings
#data["log_num_sold"] = np.log(data.num_sold + 1e-8)
#data["avg_volume_by_country"] = data.groupby(["time_idx", "country"], observed=True).num_sold.transform("mean")
#data["avg_volume_by_store"] = data.groupby(["time_idx", "store"], observed=True).num_sold.transform("mean")
#data["avg_volume_by_product"] = data.groupby(["time_idx", "product"], observed=True).num_sold.transform("mean")
#unique_dates_country = data[['date', 'Ticker']].drop_duplicates(ignore_index = True)
#unique_dates_country['is_holiday'] = (unique_dates_country
# .apply(lambda x: x.date in holidays.country_holidays(x.country), axis = 1).astype('category'))
#unique_dates_country['is_holiday_lead_1'] = (unique_dates_country
# .apply(lambda x: x.date+pd.Timedelta(days=1) in holidays.country_holidays(x.country), axis = 1).astype('category'))
#unique_dates_country['is_holiday_lead_2'] = (unique_dates_country
# .apply(lambda x: x.date+pd.Timedelta(days=2) in holidays.country_holidays(x.country), axis = 1).astype('category'))
#unique_dates_country['is_holiday_lag_1'] = (unique_dates_country
# .apply(lambda x: x.date-pd.Timedelta(days=1) in holidays.country_holidays(x.country), axis = 1).astype('category'))
#unique_dates_country['is_holiday_lag_2'] = (unique_dates_country
# .apply(lambda x: x.date-pd.Timedelta(days=2) in holidays.country_holidays(x.country), axis = 1).astype('category'))
#data = data.merge(unique_dates_country, on = ['date', 'Ticker'], validate = "m:1")
#del unique_dates_country
gc.collect()
data.sample(5, random_state=30)
train = data.iloc[:len(train)]
test = data.iloc[len(train):]
max_prediction_length = 2
max_encoder_length = train.date.nunique()
training_cutoff = train["time_idx"].max() - max_prediction_length #we will validate on 2020
# Let's create a Dataset
training = TimeSeriesDataSet(
train[lambda x: x.time_idx <= training_cutoff],
time_idx="time_idx",
target="Close",
group_ids=["Ticker"],
min_encoder_length=max_prediction_length, # keep encoder length long (as it is in the validation set)
max_encoder_length=max_encoder_length,
max_prediction_length=max_prediction_length,
static_categoricals=["Ticker"],
time_varying_known_categoricals=["month", "week_of_year", "day_of_week"],
#variable_groups={"is_holiday": ["is_holiday"]}, # group of categorical variables can be treated as one variable
time_varying_known_reals=["time_idx"],
time_varying_unknown_categoricals=[],
time_varying_unknown_reals=[
'Open','High','Low','Close','OI','RSI14','RSI44','HHRSI','Rsi Weekly','LLCHHV','white','Vap44','Vap14','Ema5','Ema20','Ema50','Ema200'
],
target_normalizer=GroupNormalizer(
groups=['Ticker'], transformation="softplus"
), # use softplus and normalize by group
categorical_encoders={
'week_of_year':NaNLabelEncoder(add_nan=True)
},
#lags={'num_sold': [7, 30, 365]},
add_relative_time_idx=True,
add_target_scales=True,
add_encoder_length=True,
)
# create validation set (predict=True) which means to predict the last max_prediction_length points in time
# for each series
validation = TimeSeriesDataSet.from_dataset(training, train, predict=True, stop_randomization=True)
# create dataloaders for model
batch_size = 128 # set this between 32 to 128
train_dataloader = training.to_dataloader(train=True, batch_size=batch_size, num_workers=0)
val_dataloader = validation.to_dataloader(train=False, batch_size=batch_size * 10, num_workers=0)
#let's see how a naive model does
actuals = torch.cat([y for x, (y, weight) in iter(val_dataloader)])#.cuda()
baseline_predictions = Baseline().predict(val_dataloader)#.cuda()
(actuals - baseline_predictions).abs().mean().item()
sm = SMAPE()
print(f"Median loss for naive prediction on validation: {sm.loss(actuals, baseline_predictions).mean(axis = 1).median().item()}")
early_stop_callback = EarlyStopping(monitor="train_loss", min_delta=1e-2, patience=PATIENCE, verbose=False, mode="min")
lr_logger = LearningRateMonitor() # log the learning rate
logger = TensorBoardLogger("lightning_logs") # logging results to a tensorboard
trainer = pl.Trainer(
max_epochs=1,
accelerator=ACCELERATOR,
enable_model_summary=False,
gradient_clip_val=0.25,
limit_train_batches=10, # coment in for training, running valiation every 30 batches
#fast_dev_run=True, # comment in to check that networkor dataset has no serious bugs
callbacks=[lr_logger, early_stop_callback],
logger=logger,
)
tft = TemporalFusionTransformer.from_dataset(
training,
learning_rate=LEARNING_RATE,
lstm_layers=2,
hidden_size=16,
attention_head_size=2,
dropout=0.2,
hidden_continuous_size=8,
output_size=1, # 7 quantiles by default
loss=SMAPE(),
log_interval=10, # uncomment for learning rate finder and otherwise, e.g. to 10 for logging every 10 batches
reduce_on_plateau_patience=4
)
tft.to(DEVICE)
trainer.fit(
tft,
train_dataloaders=train_dataloader,
val_dataloaders=val_dataloader,
)
#torch.cuda.empty_cache()
#print(f"Number of parameters in network: {tft.size()/1e3:.1f}k")
if OPTUNA:
from pytorch_forecasting.models.temporal_fusion_transformer.tuning import optimize_hyperparameters
# create study
study = optimize_hyperparameters(
train_dataloader,
val_dataloader,
model_path="optuna_test",
n_trials=5,
max_epochs=MAX_EPOCHS,
gradient_clip_val_range=(0.01, 0.3),
hidden_size_range=(8, 24),
hidden_continuous_size_range=(8, 12),
attention_head_size_range=(2, 4),
learning_rate_range=(0.01, 0.05),
dropout_range=(0.1, 0.25),
trainer_kwargs=dict(limit_train_batches=20),
reduce_on_plateau_patience=4,
pruner=optuna.pruners.MedianPruner(n_min_trials=3, n_startup_trials=3),
use_learning_rate_finder=False, # use Optuna to find ideal learning rate or use in-built learning rate finder
)
#torch.cuda.empty_cache()
#'''
trainer = pl.Trainer(
max_epochs=MAX_EPOCHS,
accelerator=ACCELERATOR,
enable_model_summary=False,
gradient_clip_val=study.best_params['gradient_clip_val'],
limit_train_batches=20, # coment in for training, running valiation every 30 batches
#fast_dev_run=True, # comment in to check that networkor dataset has no serious bugs
callbacks=[lr_logger, early_stop_callback],
logger=logger,
)
tft = TemporalFusionTransformer.from_dataset(
training,
learning_rate=study.best_params['learning_rate'],
lstm_layers=2,
hidden_size=study.best_params['hidden_size'],
attention_head_size=study.best_params['attention_head_size'],
dropout=study.best_params['dropout'],
hidden_continuous_size=study.best_params['hidden_continuous_size'],
output_size=1, # 7 quantiles by default
loss=SMAPE(),
log_interval=10, # uncomment for learning rate finder and otherwise, e.g. to 10 for logging every 10 batches
reduce_on_plateau_patience=4
)
tft.to(DEVICE)
trainer.fit(
tft,
train_dataloaders=train_dataloader,
val_dataloaders=val_dataloader,
)
#'''
#torch.cuda.empty_cache()
best_model_path = trainer.checkpoint_callback.best_model_path
best_tft = TemporalFusionTransformer.load_from_checkpoint(best_model_path)
actuals = torch.cat([y[0] for x, y in iter(val_dataloader)])#.cuda()
predictions = best_tft.predict(val_dataloader, mode="prediction")
raw_predictions = best_tft.predict(val_dataloader, mode="raw", return_x=True)
sm = SMAPE()
print(f"Validation median SMAPE loss: {sm.loss(actuals, predictions).mean(axis = 1).median().item()}")
prax[5] = sm.loss(actuals, predictions).mean(axis = 1).median().item()
#best_tft.plot_prediction(raw_predictions.x, raw_predictions.output, idx=0, add_loss_to_title=True);
print(raw_predictions[0][0])
prax[3] = '-'
prax[4] = raw_predictions[0][0].data.cpu().tolist()[0][0]
t = prax[4]
tm = data['Close'][len(data)-1]
if(t-tm>0):
prax[6] = 1
elif(t-tm==0):
prax[6] = 0
else:
prax[6] = -1
#prax[i][3] = raw_predictions[0][0].data[1]
print("-----------")
#with open("out.csv", "w", newline="") as f:
# writer = csv.writer(f)
# writer.writerows(prax)
# %%
# Function to train the model (TFT)
def modelTFT_OpenGap(csv_file, prax):
train = csv_file
#test = pd.read_csv("/kaggle/input/artemis-test/nifty_daily.csv")
train['date'] = pd.to_datetime(train['Date/Time'])
#test['date'] = pd.to_datetime(test['Date'])
datLength = len(train)
train['O-C'] = 0
for i in range(datLength):
if i == 0:
train['O-C'][i] = 0
continue
else:
train['O-C'][i] = train['Open'][i] - train['Close'][i-1]
data = pd.concat([train], axis = 0, ignore_index=True)
# Check that key is country-store-product-date combination
#assert len(data.drop_duplicates(['country', 'store', 'product', 'date'])) == len(data)
# Check that there is one date per country-store-product combination
#assert len(data.drop_duplicates(['country', 'store', 'product'])) == len(data)//data['date'].nunique()
#display(train.sample(4))
# Add a time_idx (an sequence of consecutive integers that goes from min to max date)
data = (data.merge((data[['Date/Time']].drop_duplicates(ignore_index=True)
.rename_axis('time_idx')).reset_index(), on = ['Date/Time']))
# add additional features
data["day_of_week"] = data['date'].dt.dayofweek.astype(str).astype("category") # categories have be strings
data["week_of_year"] = data['date'].dt.isocalendar().week.astype(str).astype("category") # categories have be strings
data["month"] = data['date'].dt.month.astype(str).astype("category") # categories have be strings
#data["log_num_sold"] = np.log(data.num_sold + 1e-8)
#data["avg_volume_by_country"] = data.groupby(["time_idx", "country"], observed=True).num_sold.transform("mean")
#data["avg_volume_by_store"] = data.groupby(["time_idx", "store"], observed=True).num_sold.transform("mean")
#data["avg_volume_by_product"] = data.groupby(["time_idx", "product"], observed=True).num_sold.transform("mean")
#unique_dates_country = data[['date', 'Ticker']].drop_duplicates(ignore_index = True)
#unique_dates_country['is_holiday'] = (unique_dates_country
# .apply(lambda x: x.date in holidays.country_holidays(x.country), axis = 1).astype('category'))
#unique_dates_country['is_holiday_lead_1'] = (unique_dates_country
# .apply(lambda x: x.date+pd.Timedelta(days=1) in holidays.country_holidays(x.country), axis = 1).astype('category'))
#unique_dates_country['is_holiday_lead_2'] = (unique_dates_country
# .apply(lambda x: x.date+pd.Timedelta(days=2) in holidays.country_holidays(x.country), axis = 1).astype('category'))
#unique_dates_country['is_holiday_lag_1'] = (unique_dates_country
# .apply(lambda x: x.date-pd.Timedelta(days=1) in holidays.country_holidays(x.country), axis = 1).astype('category'))
#unique_dates_country['is_holiday_lag_2'] = (unique_dates_country
# .apply(lambda x: x.date-pd.Timedelta(days=2) in holidays.country_holidays(x.country), axis = 1).astype('category'))
#data = data.merge(unique_dates_country, on = ['date', 'Ticker'], validate = "m:1")
#del unique_dates_country
gc.collect()
data.sample(5, random_state=30)
train = data.iloc[:len(train)]
test = data.iloc[len(train):]
max_prediction_length = 2
max_encoder_length = train.date.nunique()
training_cutoff = train["time_idx"].max() - max_prediction_length #we will validate on 2020
# Let's create a Dataset
training = TimeSeriesDataSet(
train[lambda x: x.time_idx <= training_cutoff],
time_idx="time_idx",
target="Close",
group_ids=["Ticker"],
min_encoder_length=max_prediction_length, # keep encoder length long (as it is in the validation set)
max_encoder_length=max_encoder_length,
max_prediction_length=max_prediction_length,
static_categoricals=["Ticker"],
time_varying_known_categoricals=["month", "week_of_year", "day_of_week"],
#variable_groups={"is_holiday": ["is_holiday"]}, # group of categorical variables can be treated as one variable
time_varying_known_reals=["time_idx"],
time_varying_unknown_categoricals=[],
time_varying_unknown_reals=[
'Open','High','Low','Close','OI','RSI14','RSI44','HHRSI','Rsi Weekly','LLCHHV','white','Vap44','Vap14','Ema5','Ema20','Ema50','Ema200', 'O-C'
],
target_normalizer=GroupNormalizer(
groups=['Ticker'], transformation="softplus"
), # use softplus and normalize by group
categorical_encoders={
'week_of_year':NaNLabelEncoder(add_nan=True)
},
#lags={'num_sold': [7, 30, 365]},
add_relative_time_idx=True,
add_target_scales=True,
add_encoder_length=True,
)
# create validation set (predict=True) which means to predict the last max_prediction_length points in time
# for each series
validation = TimeSeriesDataSet.from_dataset(training, train, predict=True, stop_randomization=True)
# create dataloaders for model
batch_size = 128 # set this between 32 to 128
train_dataloader = training.to_dataloader(train=True, batch_size=batch_size, num_workers=0)
val_dataloader = validation.to_dataloader(train=False, batch_size=batch_size * 10, num_workers=0)
#let's see how a naive model does
actuals = torch.cat([y for x, (y, weight) in iter(val_dataloader)])#.cuda()
baseline_predictions = Baseline().predict(val_dataloader)#.cuda()
(actuals - baseline_predictions).abs().mean().item()
sm = SMAPE()
print(f"Median loss for naive prediction on validation: {sm.loss(actuals, baseline_predictions).mean(axis = 1).median().item()}")
early_stop_callback = EarlyStopping(monitor="train_loss", min_delta=1e-2, patience=PATIENCE, verbose=False, mode="min")
lr_logger = LearningRateMonitor() # log the learning rate
logger = TensorBoardLogger("lightning_logs") # logging results to a tensorboard
trainer = pl.Trainer(
max_epochs=1,
accelerator=ACCELERATOR,
enable_model_summary=False,
gradient_clip_val=0.25,
limit_train_batches=10, # coment in for training, running valiation every 30 batches
#fast_dev_run=True, # comment in to check that networkor dataset has no serious bugs
callbacks=[lr_logger, early_stop_callback],
logger=logger,
)
tft = TemporalFusionTransformer.from_dataset(
training,
learning_rate=LEARNING_RATE,
lstm_layers=2,
hidden_size=16,
attention_head_size=2,
dropout=0.2,
hidden_continuous_size=8,
output_size=1, # 7 quantiles by default
loss=SMAPE(),
log_interval=10, # uncomment for learning rate finder and otherwise, e.g. to 10 for logging every 10 batches
reduce_on_plateau_patience=4
)
tft.to(DEVICE)
trainer.fit(
tft,
train_dataloaders=train_dataloader,
val_dataloaders=val_dataloader,
)
#torch.cuda.empty_cache()
#print(f"Number of parameters in network: {tft.size()/1e3:.1f}k")
if OPTUNA:
from pytorch_forecasting.models.temporal_fusion_transformer.tuning import optimize_hyperparameters
# create study
study = optimize_hyperparameters(
train_dataloader,
val_dataloader,
model_path="optuna_test",
n_trials=5,
max_epochs=MAX_EPOCHS,
gradient_clip_val_range=(0.01, 0.3),
hidden_size_range=(8, 24),
hidden_continuous_size_range=(8, 12),
attention_head_size_range=(2, 4),
learning_rate_range=(0.01, 0.05),
dropout_range=(0.1, 0.25),
trainer_kwargs=dict(limit_train_batches=20),
reduce_on_plateau_patience=4,
pruner=optuna.pruners.MedianPruner(n_min_trials=3, n_warmup_steps=3),
use_learning_rate_finder=False, # use Optuna to find ideal learning rate or use in-built learning rate finder
)
#torch.cuda.empty_cache()
#'''
trainer = pl.Trainer(
max_epochs=MAX_EPOCHS,
accelerator=ACCELERATOR,
enable_model_summary=False,
gradient_clip_val=study.best_params['gradient_clip_val'],
limit_train_batches=20, # coment in for training, running valiation every 30 batches
#fast_dev_run=True, # comment in to check that networkor dataset has no serious bugs
callbacks=[lr_logger, early_stop_callback],
logger=logger,
)
tft = TemporalFusionTransformer.from_dataset(
training,
learning_rate=study.best_params['learning_rate'],
lstm_layers=2,
hidden_size=study.best_params['hidden_size'],
attention_head_size=study.best_params['attention_head_size'],
dropout=study.best_params['dropout'],
hidden_continuous_size=study.best_params['hidden_continuous_size'],
output_size=1, # 7 quantiles by default
loss=SMAPE(),
log_interval=10, # uncomment for learning rate finder and otherwise, e.g. to 10 for logging every 10 batches
reduce_on_plateau_patience=4
)
tft.to(DEVICE)
trainer.fit(
tft,
train_dataloaders=train_dataloader,
val_dataloaders=val_dataloader,
)
#'''
#torch.cuda.empty_cache()
best_model_path = trainer.checkpoint_callback.best_model_path
best_tft = TemporalFusionTransformer.load_from_checkpoint(best_model_path)
actuals = torch.cat([y[0] for x, y in iter(val_dataloader)])#.cuda()
predictions = best_tft.predict(val_dataloader, mode="prediction")
raw_predictions = best_tft.predict(val_dataloader, mode="raw", return_x=True)
sm = SMAPE()
print(f"Validation median SMAPE loss: {sm.loss(actuals, predictions).mean(axis = 1).median().item()}")
prax[5] = sm.loss(actuals, predictions).mean(axis = 1).median().item()
#best_tft.plot_prediction(raw_predictions.x, raw_predictions.output, idx=0, add_loss_to_title=True);
print(raw_predictions[0][0])
prax[3] = '-'
prax[4] = raw_predictions[0][0].data.cpu().tolist()[0][0]
t = prax[4]
tm = data['Close'][len(data)-1]
if(t-tm>0):
prax[6] = 1
elif(t-tm==0):
prax[6] = 0
else:
prax[6] = -1
#prax[i][3] = raw_predictions[0][0].data[1]
print("-----------")
#with open("out.csv", "w", newline="") as f:
# writer = csv.writer(f)
# writer.writerows(prax)
# %%
def generate_csv(data_list):
today = date.today().strftime("%Y_%m_%d")
filename = f"result_{today}.csv"
file_exists = os.path.isfile(filename)
with open(filename, mode='a', newline='') as csv_file:
fieldnames = ['Ticker', 'Prev_Close_Real', 'Model', 'Prev_Close_Model', 'Close_Model', 'Max_Err', 'Up_Down' ] # replace with your own column names
writer = csv.writer(csv_file, delimiter=',')
if not file_exists:
writer.writerow(fieldnames) # file doesn't exist yet, write a header
writer.writerow(data_list)
csv_file.close()
def guess_date(string):
for fmt in ["%Y/%m/%d", "%d-%m-%Y", "%Y%m%d", "%m/%d/%Y", "%d/%m/%Y", "%Y-%m-%d", "%d/%m/%y", "%m/%d/%y"]:
try:
return datetime.datetime.strptime(string, fmt).date()
except ValueError:
continue
raise ValueError(string)
# %%
# Main function
def main(files):
# Get a list of all the CSV files uploaded
prax = [0,0,0,0,0,0,0]
for idx, file in enumerate(files):
print(f"File #{idx+1}: {file}")
print(file.name)
df = pd.read_csv(file.name)
print(df['Ticker'][0])
prax[0] = df['Ticker'][0]
prax[1] = df['Close'][len(df)-1]
print('------------------')
#df = df.drop(['EMARSI'], axis=1)
#df['Date/Time'] = pd.to_datetime(df['Date/Time'])
for i in range(len(df)):
x = guess_date(df['Date/Time'][i])
df['Date/Time'][i] = x.strftime("%Y-%m-%d")
df['Date/Time'] = pd.to_datetime(df['Date/Time'])
df.fillna(0, inplace=True)
#df.to_csv('out.csv')
modelTFT(df, prax)
prax[2] = "TFT"
generate_csv(prax)
modelTFT_OpenGap(df, prax)
prax[2] = "TFT_OpenGap"
generate_csv(prax)
# Generate blank line
prax=["","","","","","",""]
generate_csv(prax)
# Reset prax
prax = [0,0,0,0,0,0,0]
today = date.today().strftime("%Y_%m_%d")
return f"result_{today}.csv"
gradioApp = gr.Interface(fn=main, inputs=gr.File(file_count="multiple"), outputs="file")
if __name__ == "__main__":
# Calling main function
gradioApp.launch()
|