Make changes in file

Signed-off-by: Aadhitya A <[email protected]>

.gitignore

@@ -0,0 +1 @@
+env

app-plain.py

@@ -0,0 +1,957 @@
+# %%
+# 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)] 
+
+# %%
+# Objective function for Optuna (CNN-LSTM)
+def objective(trial, X_train, y_train, X_test, y_test):
+    model = tf.keras.Sequential()
+
+    # Creating the Neural Network model here...
+    # CNN layers
+    model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(X_train.shape[1], 1)))
+    # model.add(Dense(5, kernel_regularizer=L2(0.01)))
+
+    # LSTM layers
+    model.add(Bidirectional(LSTM(trial.suggest_int("lstm_units_1", 32, 256), return_sequences=True)))
+    model.add(Dropout(trial.suggest_float("dropout_1", 0.1, 0.5)))
+    model.add(Bidirectional(LSTM(trial.suggest_int("lstm_units_2", 32, 256), return_sequences=False)))
+    model.add(Dropout(trial.suggest_float("dropout_2", 0.1, 0.5)))
+
+    #Final layers
+    model.add(Dense(1, activation='relu'))
+    model.compile(optimizer='adam', loss='mse', metrics=['mse'])
+
+    # Train the model
+    pruning_callback = TFKerasPruningCallback(trial, "val_loss")
+    history = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=15, batch_size=32, verbose=0, callbacks=[pruning_callback])
+
+    # Evaluate the model
+    loss = model.evaluate(X_test, y_test, verbose=0)[0]
+
+    return loss
+
+# %%
+# Function to train the model (CNN-LSTM)
+def modelCNNLSTM(csv_file, prax):
+    # Read the data
+    df = csv_file
+    #df = df['Date/Time'].values.astype("float64")
+    temp_data = df.iloc[0:len(df)-100, 1:21]
+    trek = df.iloc[len(df)-100:,1:21]
+    #print(temp_data)
+    data = temp_data
+    sc = MinMaxScaler()
+    # Split the data into training and testing sets
+    train_size = int(len(data) * 0.8)
+    train_data, test_data = data[:train_size], data[train_size:]
+    # Separate the input features and target variable
+    X_train, y_train = train_data, train_data['Close']
+    X_test, y_test = test_data, test_data['Close']
+
+    X_train = X_train[0:len(X_train)-1]
+    y_train = y_train[1:len(y_train)]
+    X_test = X_test[0:len(X_test)-1]
+    y_test = y_test[1:len(y_test)]
+
+    Xt = X_train
+    Xts = X_test
+    Yt = y_train
+    Yts = y_test
+
+    y_train = y_train.values.reshape(-1,1)
+    y_test = y_test.values.reshape(-1,1)
+
+    X_train = sc.fit_transform(X_train)
+    y_train = sc.fit_transform(y_train)
+    X_test = sc.fit_transform(X_test)
+    y_test = sc.fit_transform(y_test)
+
+    x_tr=pd.DataFrame(X_train, index = Xt.index, columns = Xt.columns)
+    y_tr=pd.DataFrame(y_train, index = Yt.index)
+    x_te=pd.DataFrame(X_test, index = Xts.index, columns = Xts.columns)
+    y_te=pd.DataFrame(y_test, index = Yts.index)
+
+    # Reshape the data for the CNN-LSTM model
+    X_train = X_train.reshape((X_train.shape[0], X_train.shape[1], 1))
+    X_test = X_test.reshape((X_test.shape[0], X_test.shape[1], 1))
+
+    study = optuna.create_study(direction="minimize", pruner=optuna.pruners.MedianPruner(n_min_trials=4, n_startup_trials=4))
+    fn = lambda trial: objective(trial, X_train=X_train, X_test=X_test, y_train=y_train, y_test=y_test)
+    study.optimize(fn, n_trials=5)
+
+    best_params = study.best_params
+    #print(f"Best params: {best_params}")
+
+    model = tf.keras.Sequential()
+
+    # Creating the Neural Network model here...
+    # CNN layers
+    model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(X_train.shape[1], 1)))
+    # model.add(Dense(5, kernel_regularizer=L2(0.01)))
+
+    # LSTM layers
+    model.add(Bidirectional(LSTM(best_params["lstm_units_1"], return_sequences=True)))
+    model.add(Dropout(best_params["dropout_1"]))
+    model.add(Bidirectional(LSTM(best_params["lstm_units_2"], return_sequences=False)))
+    model.add(Dropout(best_params["dropout_2"]))
+
+    #Final layers
+    model.add(Dense(1, activation='relu'))
+    model.compile(optimizer='adam', loss='mse', metrics=['mse'])
+
+    # Train the model
+    history = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=32, verbose=0)
+
+    # Evaluate the model
+    loss = model.evaluate(X_test, y_test, verbose=0)[0]
+
+    print(f"Final loss (without KFold): {loss}")
+        
+    kfold = KFold(n_splits=10, shuffle=True)
+
+    inputs = np.concatenate((X_train, X_test), axis=0)
+    targets = np.concatenate((y_train, y_test), axis=0)
+    acc_per_fold = []
+    loss_per_fold = []
+    xgb_res = []
+    num_epochs = 10
+    batch_size = 32
+
+    fold_no = 1
+    print('------------------------------------------------------------------------')
+    print("Training for 10 folds... Standby")
+    for train, test in kfold.split(inputs, targets):
+        #print('------------------------------------------------------------------------')
+        #print(f'Training for fold {fold_no} ...')
+        history = model.fit(inputs[train], targets[train],
+                  batch_size=32,
+                  epochs=15,
+                  verbose=0)
+
+        scores = model.evaluate(inputs[test], targets[test], verbose=0)
+        #print(f'Score for fold {fold_no}: {model.metrics_names[0]} of {scores[0]}; {model.metrics_names[1]} of {scores[1]*100}%')
+        acc_per_fold.append(scores[1] * 100)
+        loss_per_fold.append(scores[0])
+        fold_no = fold_no + 1
+
+    
+    print('------------------------------------------------------------------------')
+    #print('Score per fold')
+    #for i in range(0, len(acc_per_fold)):
+    #    print('------------------------------------------------------------------------')
+    #    print(f'> Fold {i+1} - Loss: {loss_per_fold[i]} - Loss%: {acc_per_fold[i]}%')
+    #print('------------------------------------------------------------------------')
+    #print('Average scores for all folds:')
+    #print(f'> Possible Loss %: {np.mean(acc_per_fold)} (+- {np.std(acc_per_fold)})')
+    #print(f'> Loss: {np.mean(loss_per_fold)}')
+    #print('------------------------------------------------------------------------')
+    
+    trek = df.iloc[0:len(df), 1:21]
+    Y = trek[0:len(trek)]
+    YP = trek[1:len(trek)]
+    Y1 = Y['Close']
+    Y2 = YP['Close']
+    Yx = pd.DataFrame(YP, index=YP.index, columns=YP.columns)
+    #X = sc.fit_transform(X.reshape(-1,22))
+    Y = np.array(Y)
+    Y1 = np.array(Y1)
+    Y = sc.fit_transform(Y)
+    Y1 = Y1.reshape(-1,1)
+    Y1 = sc.fit_transform(Y1)
+
+    train_X = Y.reshape(Y.shape[0],Y.shape[1],1)
+    #Y = Y.reshape(-1,1)
+    pred = model.predict(train_X, verbose=0)
+    pred = np.array(pred).reshape(-1,1)
+    var2 = max_error(pred.reshape(-1,1), Y1)
+    print('Max Error: %f' % var2)
+    prax[5] = float(var2)
+    pred = sc.inverse_transform(pred)
+
+    print(pred[-2], pred[-1])
+    prax[3] = pred[-2]
+    prax[4] = pred[-1]
+    if(pred[-1]-pred[-2]>0):
+        prax[6] = 1 
+    elif(pred[-1]-pred[-2]==0):
+        prax[6] = 0
+    else:
+        prax[6] = -1
+
+# %%
+# Function to train the model (CNN-LSTM)
+def modelCNNLSTM_OpenGap(csv_file, prax):
+    # Read the data
+    df = csv_file
+    datLength = len(df)
+    df['O-C'] = 0
+    for i in range(datLength):
+        if i == 0:
+            df['O-C'][i] = 0
+            continue
+        else:
+            df['O-C'][i] = df['Open'][i] - df['Close'][i-1]
+    temp_data = df.iloc[0:datLength-100, 1:22]
+    trek = df.iloc[datLength-100:,1:22]
+    #print(temp_data)
+    data = temp_data
+    #data = data.values.astype("float64")
+    sc = MinMaxScaler()
+    # Split the data into training and testing sets
+    train_size = int(len(data) * 0.8)
+    train_data, test_data = data[:train_size], data[train_size:]
+
+    # Separate the input features and target variable
+    X_train, y_train = train_data, train_data['Close']
+    X_test, y_test = test_data, test_data['Close']
+
+    X_train = X_train[0:len(X_train)-1]
+    y_train = y_train[1:len(y_train)]
+    X_test = X_test[0:len(X_test)-1]
+    y_test = y_test[1:len(y_test)]
+
+    Xt = X_train
+    Xts = X_test
+    Yt = y_train
+    Yts = y_test
+
+    y_train = y_train.values.reshape(-1,1)
+    y_test = y_test.values.reshape(-1,1)
+
+    X_train = sc.fit_transform(X_train)
+    y_train = sc.fit_transform(y_train)
+    X_test = sc.fit_transform(X_test)
+    y_test = sc.fit_transform(y_test)
+
+    x_tr=pd.DataFrame(X_train, index = Xt.index, columns = Xt.columns)
+    y_tr=pd.DataFrame(y_train, index = Yt.index)
+    x_te=pd.DataFrame(X_test, index = Xts.index, columns = Xts.columns)
+    y_te=pd.DataFrame(y_test, index = Yts.index)
+
+    # Reshape the data for the CNN-LSTM model
+    X_train = X_train.reshape((X_train.shape[0], X_train.shape[1], 1))
+    X_test = X_test.reshape((X_test.shape[0], X_test.shape[1], 1))
+
+    study = optuna.create_study(direction="minimize", pruner=optuna.pruners.MedianPruner(n_min_trials=2, n_startup_trials=2))
+    fn = lambda trial: objective(trial, X_train=X_train, X_test=X_test, y_train=y_train, y_test=y_test)
+    study.optimize(fn, n_trials=5)
+
+    best_params = study.best_params
+    #print(f"Best params: {best_params}")
+
+    model = tf.keras.Sequential()
+
+    # Creating the Neural Network model here...
+    # CNN layers
+    model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(X_train.shape[1], 1)))
+    # model.add(Dense(5, kernel_regularizer=L2(0.01)))
+
+    # LSTM layers
+    model.add(Bidirectional(LSTM(best_params["lstm_units_1"], return_sequences=True)))
+    model.add(Dropout(best_params["dropout_1"]))
+    model.add(Bidirectional(LSTM(best_params["lstm_units_2"], return_sequences=False)))
+    model.add(Dropout(best_params["dropout_2"]))
+
+    #Final layers
+    model.add(Dense(1, activation='relu'))
+    model.compile(optimizer='adam', loss='mse', metrics=['mse'])
+
+    # Train the model
+    history = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=32, verbose=0)
+
+    # Evaluate the model
+    loss = model.evaluate(X_test, y_test, verbose=0)[0]
+
+    print(f"Final loss (without KFold): {loss}")
+        
+    kfold = KFold(n_splits=10, shuffle=True)
+
+    inputs = np.concatenate((X_train, X_test), axis=0)
+    targets = np.concatenate((y_train, y_test), axis=0)
+    acc_per_fold = []
+    loss_per_fold = []
+    xgb_res = []
+    num_epochs = 10
+    batch_size = 32
+
+    fold_no = 1
+    print('------------------------------------------------------------------------')
+    print("Training for 10 folds... Standby")
+    for train, test in kfold.split(inputs, targets):
+        #print('------------------------------------------------------------------------')
+        #print(f'Training for fold {fold_no} ...')
+        history = model.fit(inputs[train], targets[train],
+                  batch_size=32,
+                  epochs=15,
+                  verbose=0)
+
+        scores = model.evaluate(inputs[test], targets[test], verbose=0)
+        #print(f'Score for fold {fold_no}: {model.metrics_names[0]} of {scores[0]}; {model.metrics_names[1]} of {scores[1]*100}%')
+        acc_per_fold.append(scores[1] * 100)
+        loss_per_fold.append(scores[0])
+        fold_no = fold_no + 1
+
+    
+    print('------------------------------------------------------------------------')
+    #print('Score per fold')
+    #for i in range(0, len(acc_per_fold)):
+    #    print('------------------------------------------------------------------------')
+    #    print(f'> Fold {i+1} - Loss: {loss_per_fold[i]} - Loss%: {acc_per_fold[i]}%')
+    #print('------------------------------------------------------------------------')
+    #print('Average scores for all folds:')
+    #print(f'> Possible Loss %: {np.mean(acc_per_fold)} (+- {np.std(acc_per_fold)})')
+    #print(f'> Loss: {np.mean(loss_per_fold)}')
+    #print('------------------------------------------------------------------------')
+    
+    trek = df.iloc[0:len(df), 1:22]
+    Y = trek[0:len(trek)]
+    YP = trek[1:len(trek)]
+    Y1 = Y['Close']
+    Y2 = YP['Close']
+    Yx = pd.DataFrame(YP, index=YP.index, columns=YP.columns)
+    #X = sc.fit_transform(X.reshape(-1,22))
+    Y = np.array(Y)
+    Y1 = np.array(Y1)
+    Y = sc.fit_transform(Y)
+    Y1 = Y1.reshape(-1,1)
+    Y1 = sc.fit_transform(Y1)
+
+    train_X = Y.reshape(Y.shape[0],Y.shape[1],1)
+    #Y = Y.reshape(-1,1)
+    pred = model.predict(train_X, verbose=0)
+    pred = np.array(pred).reshape(-1,1)
+    var2 = max_error(pred.reshape(-1,1), Y1)
+    print('Max Error: %f' % var2)
+    prax[5] = float(var2)
+    pred = sc.inverse_transform(pred)
+
+    print(pred[-2], pred[-1])
+    prax[3] = pred[-2]
+    prax[4] = pred[-1]
+    if(pred[-1]-pred[-2]>0):
+        prax[6] = 1 
+    elif(pred[-1]-pred[-2]==0):
+        prax[6] = 0
+    else:
+        prax[6] = -1
+
+# %%
+# 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))
+
+    """<a id ="3"></a><h3 style="background:#0554f2; border:0; border-radius: 4px; color:#f5f6f7">Model Implementation in Pytorch-Forecasting </h3>"""
+
+    # 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))
+
+    """<a id ="3"></a><h3 style="background:#0554f2; border:0; border-radius: 4px; color:#f5f6f7">Model Implementation in Pytorch-Forecasting </h3>"""
+
+    # 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():
+    # Data loading
+    path = "./demo"
+    print("Searching CSV files in ", path, "...")
+    # path = "/kaggle/input/artemis-test"
+
+    # Get a list of all the CSV files in the folder
+    csv_files = glob.glob(path + "/*.csv")
+    prax = [0,0,0,0,0,0,0]
+    # Create a list of DataFrames, one for each CSV file
+    dfs = []
+    c = 0
+    for csv_file in csv_files:
+        df = pd.read_csv(csv_file)
+        dfs.append(df)
+        c = c + 1
+
+    if c == 0:
+        print("No CSV files found in ", path, ".")
+        print("Exiting...")
+
+    for df in dfs:
+        #print(df.head())
+        print(df['Ticker'][0])
+        prax[0] = df['Ticker'][0]
+        prax[1] = df['Close'][len(df)-1]
+        print('------------------')
+        #df = df.drop(['Volume'], axis=1)
+        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)
+        modelTFT(df, prax)
+        prax[2] = "TFT"
+        generate_csv(prax)
+        prax = [0,0,0,0,0,0,0]
+        modelTFT_OpenGap(df, prax)
+        prax[2] = "TFT_OpenGap"
+        generate_csv(prax)
+        #df.set_index('Date/Time', inplace=True)
+        df = df.drop(['Date/Time'], axis=1)
+        prax = [0,0,0,0,0,0,0]
+        modelCNNLSTM(df, prax)
+        prax[2] = "CNNLSTM"
+        generate_csv(prax)
+        prax = [0,0,0,0,0,0,0]
+        modelCNNLSTM_OpenGap(df, prax)
+        prax[2] = "CNNLSTM_OpenGap"
+        #print("Saving to CSV...Standby...")
+        generate_csv(prax)
+        # Generate blank line
+        prax=["","","","","","",""]
+        generate_csv(prax)
+        # Reset prax
+        prax = [0,0,0,0,0,0,0]
+
+if __name__ == "__main__":
+    main()
+
+    print("Deleting temporary log files...")
+    # Delete "lightning_logs" directory
+    if os.path.exists("lightning_logs"):
+        shutil.rmtree("lightning_logs")
+    # Delete "optuna_test" directory
+    if os.path.exists("optuna_test"):
+        shutil.rmtree("optuna_test")

app.py

@@ -108,9 +108,9 @@ def objective(trial, X_train, y_train, X_test, y_test):
 def modelCNNLSTM(csv_file, prax):
     # Read the data
     df = csv_file
-    df = df['Date/Time'].values.astype("float64")
-    temp_data = df.iloc[0:len(df)-100, 1:23]
-    trek = df.iloc[len(df)-100:,1:23]
+    #df = df['Date/Time'].values.astype("float64")
+    temp_data = df.iloc[0:len(df)-100, 1:21]
+    trek = df.iloc[len(df)-100:,1:21]
     #print(temp_data)
     data = temp_data
     sc = MinMaxScaler()
@@ -148,9 +148,9 @@ def modelCNNLSTM(csv_file, prax):
     X_train = X_train.reshape((X_train.shape[0], X_train.shape[1], 1))
     X_test = X_test.reshape((X_test.shape[0], X_test.shape[1], 1))
 
-    study = optuna.create_study(direction="minimize", pruner=optuna.pruners.MedianPruner(n_min_trials=5, n_startup_trials=5))
+    study = optuna.create_study(direction="minimize", pruner=optuna.pruners.MedianPruner(n_min_trials=4, n_startup_trials=4))
     fn = lambda trial: objective(trial, X_train=X_train, X_test=X_test, y_train=y_train, y_test=y_test)
-    study.optimize(fn, n_trials=7)
+    study.optimize(fn, n_trials=5)
 
     best_params = study.best_params
     #print(f"Best params: {best_params}")
@@ -219,7 +219,7 @@ def modelCNNLSTM(csv_file, prax):
     #print(f'> Loss: {np.mean(loss_per_fold)}')
     #print('------------------------------------------------------------------------')
     
-    trek = df.iloc[0:len(df), 1:23]
+    trek = df.iloc[0:len(df), 1:21]
     Y = trek[0:len(trek)]
     YP = trek[1:len(trek)]
     Y1 = Y['Close']
@@ -264,8 +264,8 @@ def modelCNNLSTM_OpenGap(csv_file, prax):
             continue
         else:
             df['O-C'][i] = df['Open'][i] - df['Close'][i-1]
-    temp_data = df.iloc[0:datLength-100, 1:24]
-    trek = df.iloc[datLength-100:,1:24]
+    temp_data = df.iloc[0:datLength-100, 1:22]
+    trek = df.iloc[datLength-100:,1:22]
     #print(temp_data)
     data = temp_data
     #data = data.values.astype("float64")
@@ -305,9 +305,9 @@ def modelCNNLSTM_OpenGap(csv_file, prax):
     X_train = X_train.reshape((X_train.shape[0], X_train.shape[1], 1))
     X_test = X_test.reshape((X_test.shape[0], X_test.shape[1], 1))
 
-    study = optuna.create_study(direction="minimize", pruner=optuna.pruners.MedianPruner(n_min_trials=5, n_startup_trials=5))
+    study = optuna.create_study(direction="minimize", pruner=optuna.pruners.MedianPruner(n_min_trials=2, n_startup_trials=2))
     fn = lambda trial: objective(trial, X_train=X_train, X_test=X_test, y_train=y_train, y_test=y_test)
-    study.optimize(fn, n_trials=7)
+    study.optimize(fn, n_trials=5)
 
     best_params = study.best_params
     #print(f"Best params: {best_params}")
@@ -376,7 +376,7 @@ def modelCNNLSTM_OpenGap(csv_file, prax):
     #print(f'> Loss: {np.mean(loss_per_fold)}')
     #print('------------------------------------------------------------------------')
     
-    trek = df.iloc[0:len(df), 1:24]
+    trek = df.iloc[0:len(df), 1:22]
     Y = trek[0:len(trek)]
     YP = trek[1:len(trek)]
     Y1 = Y['Close']
@@ -477,7 +477,7 @@ def modelTFT(csv_file, prax):
         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','BV11','SV11','Ema5','Ema20','Ema50','Ema200'
+            '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"
@@ -709,7 +709,7 @@ def modelTFT_OpenGap(csv_file, prax):
         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','BV11','SV11','Ema5','Ema20','Ema50','Ema200', 'O-C'
+            '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"
@@ -867,7 +867,8 @@ def modelTFT_OpenGap(csv_file, prax):
 
 # %%
 def generate_csv(data_list):
-    filename = f"result.csv"
+    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
@@ -936,7 +937,6 @@ def main(files):
 
 gradioApp = gr.Interface(fn=main, inputs=gr.File(file_count="multiple", file_type=".csv"), outputs="file")
 
-
 if __name__ == "__main__":
     # Calling main function
     gradioApp.launch()