Modify this code in this code the model should consider past 100 values in LSTM also add…
- User
Modify this code in this code the model should consider past 100 values in LSTM also add some more LSTM layers with 0.2 dropout value: import yfinance as yf import pandas as pd import numpy as np
nifty_df = yf.download('^NSEI', start='2009-01-01', end='2021-12-31')
Clean the data
nifty_df = nifty_df.dropna()
Calculate various percent differences
nifty_df['PctOpenClose'] = (nifty_df['Close'] - nifty_df['Open']) / nifty_df['Open'] * 100 nifty_df['PctHighLow'] = (nifty_df['High'] - nifty_df['Low']) / nifty_df['Low'] * 100 nifty_df['PctChange'] = nifty_df['Close'].pct_change() * 100
Remove the first row with NaN in 'PctChange'
nifty_df = nifty_df.iloc[1:]
Export cleaned dataset
nifty_df.to_csv('nifty_cleaned.csv')
def create_labels(df, col_name, threshold=0.5): labels = [] for index, row in df.iterrows(): future_price = row[col_name] if future_price >= threshold: labels.append(1) # Buy elif future_price <= -threshold: labels.append(-1) # Sell else: labels.append(0) # Hold
return labelsnifty_df['Labels'] = create_labels(nifty_df, 'PctChange')
import matplotlib.pyplot as plt import seaborn as sns
sns.countplot(nifty_df['Labels'])
plt.title('Count of Buy, Hold, and Sell') plt.xlabel('Trade Decisions') plt.ylabel('Count') plt.show()
from sklearn.ensemble import ExtraTreesClassifier
X = nifty_df.drop(['Labels'], axis=1) y = nifty_df['Labels']
Fit the ExtraTreesClassifier
et_clf = ExtraTreesClassifier() et_clf.fit(X, y)
Visualize feature importances
feature_importances = pd.Series(et_clf.feature_importances_, index=X.columns) feature_importances.nlargest(10).plot(kind='barh') plt.show()
important_features = feature_importances.nlargest(8).index.tolist() X_filtered = X[important_features] X_filtered
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler() scaled_X = scaler.fit_transform(X_filtered)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(scaled_X, y, test_size=0.2, random_state=42)
from keras.models import Sequential from keras.layers import LSTM, Dense
model = Sequential() model.add(LSTM(100, activation='relu', return_sequences=True, input_shape=(8, 1))) model.add(LSTM(100, activation='relu')) model.add(Dense(3))
model.compile(optimizer='adam', loss='mse')
X_train = X_train.reshape((X_train.shape[0], X_train.shape[1], 1)) model.fit(X_train, y_train, epochs=200, verbose=1)
from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score, accuracy_score
X_test = X_test.reshape((X_test.shape[0], X_test.shape[1], 1)) y_pred = model.predict(X_test)
Convert continuous output values to integer class labels
y_pred_labels = np.argmax(y_pred, axis=1) - 1 # Subtract 1 to map back to -1, 0, 1
print("Confusion Matrix:") print(confusion_matrix(y_test, y_pred_labels))
print("\n Evaluation Metrics:") print("Accuracy: ", accuracy_score(y_test, y_pred_labels)) print("Precision: ", precision_score(y_test, y_pred_labels, average='macro')) print("Recall: ", recall_score(y_test, y_pred_labels, average='macro')) print("F1-Score: ", f1_score(y_test, y_pred_labels, average='macro'))
model.save('nifty_lstm_model.h5')
Import the necessary libraries
from keras.models import load_model
Load the trained model
trained_model = load_model('nifty_lstm_model.h5')
Load the new dataset for prediction
new_data = pd.read_csv('new_data.csv')
Preprocess the new dataset
preprocessed_new_data = preprocess_data(new_data) # Assumes the same preprocessing is applied as before
Predict
predicted_labels = trained_model.predict(preprocessed_new_data)
- Assistant
Here's the modified code with an LSTM that considers past 100 values and added LSTM layers with 0.2 dropout value:
import yfinance as yf import pandas as pd import numpy as np nifty_df = yf.download('^NSEI', start='2009-01-01', end='2021-12-31') nifty_df = nifty_df.dropna() nifty_df['PctOpenClose'] = (nifty_df['Close'] - nifty_df['Open']) / nifty_df['Open'] * 100 nifty_df['PctHighLow'] = (nifty_df['High'] - nifty_df['Low']) / nifty_df['Low'] * 100 nifty_df['PctChange'] = nifty_df['Close'].pct_change() * 100 nifty_df = nifty_df.iloc[1:] nifty_df.to_csv('nifty_cleaned.csv') def create_labels(df, col_name, threshold=0.5): labels = [] for index, row in df.iterrows(): future_price = row[col_name] if future_price >= threshold: labels.append(1) # Buy elif future_price <= -threshold: labels.append(-1) # Sell else: labels.append(0) # Hold return labels nifty_df['Labels'] = create_labels(nifty_df, 'PctChange') import matplotlib.pyplot as plt import seaborn as sns sns.countplot(nifty_df['Labels']) plt.title('Count of Buy, Hold, and Sell') plt.xlabel('Trade Decisions') plt.ylabel('Count') plt.show() from sklearn.ensemble import ExtraTreesClassifier X = nifty_df.drop(['Labels'], axis=1) y = nifty_df['Labels'] et_clf = ExtraTreesClassifier() et_clf.fit(X, y) feature_importances = pd.Series(et_clf.feature_importances_, index=X.columns) feature_importances.nlargest(10).plot(kind='barh') plt.show() important_features = feature_importances.nlargest(8).index.tolist() X_filtered = X[important_features] X_filtered from sklearn.preprocessing import MinMaxScaler scaler = MinMaxScaler() scaled_X = scaler.fit_transform(X_filtered) from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(scaled_X, y, test_size=0.2, random_state=42) from keras.models import Sequential from keras.layers import LSTM, Dense, Dropout look_back = 100 def create_dataset(X, y, look_back=100): dataX, dataY = [], [] for i in range(len(X)-look_back-1): dataX.append(X[i:(i+look_back), :]) dataY.append(y[i + look_back]) return np.array(dataX), np.array(dataY) X_train_lstm, y_train_lstm = create_dataset(X_train, y_train, look_back) X_test_lstm, y_test_lstm = create_dataset(X_test, y_test, look_back) model = Sequential() model.add(LSTM(100, activation='relu', return_sequences=True, input_shape=(look_back, 8))) model.add(Dropout(0.2)) model.add(LSTM(100, activation='relu', return_sequences=True)) model.add(Dropout(0.2)) model.add(LSTM(100, activation='relu')) model.add(Dropout(0.2)) model.add(Dense(3, activation='softmax')) model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) model.fit(X_train_lstm, y_train_lstm, epochs=200, verbose=1) from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score, accuracy_score y_pred = model.predict(X_test_lstm) y_pred_labels = np.argmax(y_pred, axis=1) - 1 print("Confusion Matrix:") print(confusion_matrix(y_test_lstm, y_pred_labels)) print("\n Evaluation Metrics:") print("Accuracy: ", accuracy_score(y_test_lstm, y_pred_labels)) print("Precision: ", precision_score(y_test_lstm, y_pred_labels, average='macro')) print("Recall: ", recall_score(y_test_lstm, y_pred_labels, average='macro')) print("F1-Score: ", f1_score(y_test_lstm, y_pred_labels, average='macro')) model.save('nifty_lstm_model.h5') from keras.models import load_model trained_model = load_model('nifty_lstm_model.h5') new_data = pd.read_csv('new_data.csv') preprocessed_new_data = preprocess_data(new_data) predicted_labels = trained_model.predict(preprocessed_new_data)In this modified code, I have updated the LSTM input to consider the past 100 values and added some more LSTM layers with a 0.2 dropout value. Note that I changed the loss function to 'sparse_categorical_crossentropy' and added 'softmax' activation in the last Dense layer because it's required for the multi-class classification problem.