Create app.py

app.py

@@ -0,0 +1,105 @@
+import os
+import pandas as pd
+import tensorflow as tf
+import numpy as np
+data=pd.read_csv('train.csv')
+data.head(5)
+
+from tensorflow.keras.layers import TextVectorization
+
+x=data['comment_text']
+y=data[data.columns[2:]].values
+
+max_features=200000
+vectorizer=TextVectorization(max_tokens=max_features,
+                            output_sequence_length=1800,
+                            output_mode='int')
+vectorizer.get_vocabulary()
+vectorizer.adapt(x.values)
+vectorizer("have you watched breaking bad")[:5]
+vectorized_text=vectorizer(x.values)
+dataset=tf.data.Dataset.from_tensor_slices((vectorized_text, y))
+dataset=dataset.cache()
+dataset=dataset.shuffle(160000)
+dataset=dataset.batch(16)
+dataset=dataset.prefetch(8)
+
+batch_x, batch_y = dataset.as_numpy_iterator().next()
+
+train=dataset.take(int(len(dataset)*.7))
+val=dataset.skip(int(len(dataset)*.7)).take(int(len(dataset)*.2))
+test=dataset.skip(int(len(dataset)*.9)).take(int(len(dataset)*.1))
+
+train_generator=train.as_numpy_iterator()
+train_generator.next()
+
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import LSTM, Dropout, Bidirectional, Dense, Embedding
+
+model=Sequential()
+model.add(Embedding(max_features+1, 32))
+model.add(Bidirectional(LSTM(32, activation='tanh')))
+model.add(Dense(128, activation='relu'))
+model.add(Dense(256, activation='relu'))
+model.add(Dense(128, activation='relu'))
+model.add(Dense(6, activation='sigmoid'))
+model.compile(loss='BinaryCrossentropy', optimizer='adam', metrics=['accuracy'])
+
+model.summary()
+
+history=model.fit(train, epochs=10, validation_data=val)
+
+model.evaluate(test)
+
+x_batch, y_batch = test.as_numpy_iterator().next()
+(model.predict(x_batch) > 0.5).astype(int)
+input_text=vectorizer('I am coming to kill you pal')
+
+input_text[:7]
+batch=test.as_numpy_iterator().next()
+res=model.predict(np.expand_dims(input_text,0))
+res
+model.save('finalprojecttoxic.h5')
+
+from transformers import pipeline
+
+import gradio as gr
+
+model=tf.keras.models.load_model('finalprojecttoxic.h5')
+input_str=vectorizer('Hey i freaking hate you!. I\'m going to hurt you!')
+res=model.predict(np.expand_dims(input_str,0))
+
+
+translator_hindi = pipeline("translation", model="Helsinki-NLP/opus-mt-hi-en", tokenizer="Helsinki-NLP/opus-mt-hi-en")
+hindi_text = "नमस्ते, आप कैसे हैं?"
+en_to_hin = translator_hindi(hindi_text)
+en_to_hin[0]['translation_text']
+
+def translate_hindi(from_text):
+    result2 = translator_hindi(from_text)
+    
+    return result2[0]['translation_text']
+
+
+translate_hindi('नमस्ते, आप कैसे हैं?')
+
+def score_comment(comment):
+    vectorized_comment = vectorizer([comment])
+    results=model.predict(vectorized_comment)
+    
+    text=''
+    for idx, col in enumerate(data.columns[2:]):
+        text+= '{}: {}\n'.format(col, results[0][idx]>0.5)
+        
+    return text
+
+def combined_models(input):
+    output1=translate_hindi(input)
+    output2=score_comment(input)
+    
+    return output1, output2
+
+interface = gr.Interface(fn=combined_models, inputs="text", outputs=["text","text"],title="Toxic Comment Analyzer")
+
+interface.launch(share=True)
+