Create app.py

app.py

@@ -0,0 +1,25 @@
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import MinMaxScaler
+from transformers import AutoTokenizer
+
+# Load data
+df = pd.read_csv('NIFTY_OPTION_CHAIN_data.csv')
+
+# Handle missing values
+df.fillna(df.mean(), inplace=True)
+
+# Normalize numerical columns
+scaler = MinMaxScaler()
+df[['open', 'high', 'low', 'close', 'volume', 'oi']] = scaler.fit_transform(df[['open', 'high', 'low', 'close', 'volume', 'oi']])
+
+# Tokenize categorical columns
+tokenizer = AutoTokenizer.from_pretrained('llama-3.1')
+df['Index'] = tokenizer.encode(df['Index'], return_tensors='pt')
+df['Expiry'] = tokenizer.encode(df['Expiry'], return_tensors='pt')
+df['OptionType'] = tokenizer.encode(df['OptionType'], return_tensors='pt')
+
+# Convert datetime columns
+df['datetime'] = pd.to_datetime(df['datetime'])
+df['date'] = df['datetime'].dt.date
+df['time'] = df['datetime'].dt.time