Upload 9 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,22 @@
+import tensorflow as tf
+import gradio as gr
+
+
+model = tf.keras.models.load_model('model')
+
+def predict_spam(message):
+    pred_prob = model.predict([message])[0][0]
+    label = "Spam" if pred_prob > 0.5 else "Ham"
+    confidence = f"{pred_prob * 100:.2f}%" if label == "Spam" else f"{(1 - pred_prob) * 100:.2f}%"
+    return f"{label} ({confidence})"
+
+
+iface = gr.Interface(
+    fn=predict_spam, 
+    inputs="text", 
+    outputs="text",
+    title="Ham or Spam Classifier",
+    description="A Ham or Spam Classifier created using TensorFlow. Input a message to see if it's classified as Ham or Spam!",
+)
+
+iface.launch(share=True)

main.py

@@ -0,0 +1,73 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+import tensorflow as tf
+import numpy as np
+
+# Assuming your CSV file is named 'spam.csv' and has a header row
+df = pd.read_csv("ham or spam rnn/spam.csv", encoding="ISO-8859-1")
+
+df["class"] = df["class"].apply(lambda x: 0 if x == "ham" else 1)
+X = df["message"]
+y = df["class"]
+
+# Split the data into training and testing sets (67% training, 33% testing)
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+train_dataset = tf.data.Dataset.from_tensor_slices((X_train, y_train))
+test_dataset = tf.data.Dataset.from_tensor_slices((X_test, y_test))
+
+
+
+
+
+
+
+
+
+
+# Adapt the encoder to only the text samples before batching
+VOCAB_SIZE = 1000
+encoder = tf.keras.layers.TextVectorization(max_tokens=VOCAB_SIZE)
+encoder.adapt(train_dataset.map(lambda text, label: text)) # Unbatched dataset
+
+# Batch the datasets
+batch_size = 32
+train_dataset = train_dataset.batch(batch_size)
+test_dataset = test_dataset.batch(batch_size)
+
+
+
+
+
+
+
+
+
+
+
+
+model = tf.keras.Sequential([
+    encoder,
+    tf.keras.layers.Embedding(input_dim=len(encoder.get_vocabulary()),output_dim=64,mask_zero=True),
+    tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(64)),
+    tf.keras.layers.Dense(64, activation='relu'),
+    tf.keras.layers.Dense(1, activation='sigmoid') # Add sigmoid activation for binary classification
+])
+
+
+
+
+
+model.compile(loss=tf.keras.losses.BinaryCrossentropy(from_logits=False),
+              optimizer=tf.keras.optimizers.Adam(1e-4),
+              metrics=['accuracy'])
+
+history = model.fit(train_dataset, epochs=15, validation_data=test_dataset, validation_steps=30)
+
+test_loss, test_acc = model.evaluate(test_dataset)
+
+print('Test Loss:', test_loss)
+print('Test Accuracy:', test_acc)
+
+model.save('ham or spam rnn/model')
+

model/fingerprint.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288d85bd41a744288499f8596f65a154c23438bd90fd77c8ed4d5336f1216ecc
+size 57

model/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c476b4fe4ca5ff031f780c8601c5f16b27e113d29c563f0c5c67c0f1dad91a
+size 20219

model/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c8e8742c3789996f30e06495898505dcbc38c9974bfaf5893514d47439e9a8a
+size 5050101

model/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2ac8bb8d57c7c73d1b9c7f3ed0fd0637af012c554a39120ceef1d39b696d7a
+size 1673052

requirements.txt

@@ -0,0 +1,2 @@
+tensorflow
+gradio