Update README.md

README.md

@@ -0,0 +1,95 @@
+# News Classifier -- The Evaluation Pipeline
+## The colab link: https://colab.research.google.com/drive/1OmIHVN0joIgjGgYCdqLu2EO2By4yT5Xd#scrollTo=MsmKRoHuHyIp
+## Ziao You, Samuel Vara, Surya Sandeep Akella
+----------------------
+
+## The codes here are the same as the colab link. It shows how to call our model to evaluate the test set. Please use the colab link for easier usage.
+##
+
+----------------------
+
+### pip install package
+```
+!pip install datasets > delete.txt
+```
+
+### !!! Load Test Set -- Change the file path of test set
+```
+import pandas as pd
+df_test = pd.read_csv('/content/test_data.csv',index_col="Unnamed: 0")
+df_test.head()
+```
+
+### Load Model from Hugging Face Hub (Don't change)
+```
+from huggingface_hub import snapshot_download
+import keras
+
+# Download model from hugging face
+local_path = snapshot_download(repo_id="HermesPenn/athena_model")
+
+# Load model from local
+model = keras.saving.load_model(local_path)
+```
+### Load Training set (Don't change)
+```
+from datasets import load_dataset
+
+dataset = load_dataset("HermesPenn/athena_data")
+dataset = dataset['train']
+data = dataset.to_pandas()
+data.head()
+```
+
+### Fit_transform label_encoder and tokenizer (Don't change)
+```
+from sklearn.preprocessing import LabelEncoder
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.preprocessing.text import Tokenizer
+# Data preprocessing
+le = LabelEncoder()
+data['label'] = le.fit_transform(data['source'])
+X = data['title']
+y = data['label']
+
+# Tokenize and pad text data
+tokenizer = Tokenizer(num_words=20000, oov_token="<OOV>")
+tokenizer.fit_on_texts(X)
+X_seq = tokenizer.texts_to_sequences(X)
+X_padded = pad_sequences(X_seq, maxlen=200, padding='post', truncating='post')
+```
+
+### Test set Evaluation (Don't change)
+
+```
+from sklearn.metrics import classification_report
+
+X_test = df_test['title']
+y_test = df_test['label']
+
+
+X_test_seq = tokenizer.texts_to_sequences(X_test)
+X_test_padded = pad_sequences(X_test_seq, maxlen=200, padding='post', truncating='post')
+
+# Predict the labels using the model
+y_pred_probs = model.predict(X_test_padded)
+y_pred = (y_pred_probs > 0.5).astype(int)
+
+# Evaluate the model
+print("Classification Report:")
+print(classification_report(y_test, y_pred))
+
+
+try:
+news_outlets = le.inverse_transform(y_pred.flatten()) # le must be pre-fitted
+df_test['Predicted News Outlet'] = news_outlets
+except NameError:
+df_test['Predicted News Outlet'] = y_pred.flatten()
+```
+
+```
+# Display test set with predictions
+print("\nTest Set with Predictions:")
+
+df_test[['title', 'News Outlet', 'Predicted News Outlet']]
+```