Update app.py

app.py

@@ -6,8 +6,6 @@ model = tf.saved_model.load('arabert_pretrained')
 
 
 
-import pandas as pd
-df = pd.read_csv('put\data_cleaned1.csv')
 
 
 from transformers import TFAutoModel, AutoTokenizer
@@ -17,32 +15,8 @@ arabert_tokenizer = AutoTokenizer.from_pretrained('aubmindlab/bert-base-arabert'
 
 import pandas as pd
 
-# Assuming your DataFrame is named 'df'
-# Split the DataFrame into two parts: label=1 and label=0
-label_1_df = df[df['data_labels'] == 1]
-label_0_df = df[df['data_labels'] == 0]
-
-# Sample an equal number of rows from each label
-sample_size = min(len(label_1_df), len(label_0_df))
-sample_label_1 = label_1_df.sample(n=sample_size, random_state=42)
-sample_label_0 = label_0_df.sample(n=sample_size, random_state=42)
-
-# Concatenate the two samples to get the final balanced sample
-balanced_sample = pd.concat([sample_label_1, sample_label_0])
-
-# Shuffle the rows in the balanced sample
-balanced_sample = balanced_sample.sample(frac=1, random_state=42)
-
-
-balanced_sample.reset_index(inplace=True,drop=True)
-
-
-from sklearn.model_selection import train_test_split
 
-tweets = balanced_sample['cleaned_text']
-labels = balanced_sample['data_labels']
 
-X_train, X_test, y_train, y_test = train_test_split(tweets, labels,stratify=labels, test_size=0.15, random_state=1)
 def preprocess_input_data(texts, tokenizer, max_len=120):
     """Tokenize and preprocess the input data for Arabert model.