upload app file

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

.gitignore

@@ -0,0 +1,3 @@
+**/__pycache__/
+**venv/
+model_with_bert_multilingual.h5

README.md

@@ -1,13 +1,13 @@
----
-title: Multitask Classifying Emotion Toxicity Valorant Chat
-emoji: 📊
-colorFrom: blue
-colorTo: purple
-sdk: streamlit
-sdk_version: 1.34.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Multitask Classifying Emotion Toxicity Valorant Chat
+emoji: 📊
+colorFrom: blue
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.34.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,66 @@
+import streamlit as st
+
+from pipeline.model import MultiTaskModel
+from pipeline.preprocessing import Preprocessor
+
+# Load the model
+EMOTION_CHOICES = (
+    "Angry",
+    "Disgust",
+    "Happy",
+    "Neutral",
+    "Sad",
+    "Surprise",
+)
+TOXICITY_CHOICES = (
+    "Blaming Others",
+    "Cyberbullying",
+    "Gameplay Experience Complaints",
+    "Gamesplaining",
+    "Multiple Discrimination",
+    "Not Toxic",
+    "Sarcasm",
+)
+
+st.title("Emotion and Toxicity Classification of Valorant chat messages")
+
+st.write(
+    'This is a simple web app that predicts the emotion and toxicity of Valorant chat messages. Enter a message in the text box below and click the "Predict" button to get the prediction.'
+)
+
+st.table(
+    {
+        "Emotion": EMOTION_CHOICES,
+        "Toxicity": TOXICITY_CHOICES,
+    }
+)
+
+@st.cache_resource
+def loading_model():
+    return MultiTaskModel(preprocessor=Preprocessor())
+
+model = loading_model()
+
+# Get user input
+user_input = st.text_input("Enter a Valorant chat message:")
+st.write("You entered:", user_input)
+
+# Predict
+prediction = model.predict(user_input)
+emotions, toxicitys = prediction
+
+col1, col2 = st.columns(2)
+
+with col1:
+    for i, emotion in enumerate(emotions[0]):
+        st.write(f"{EMOTION_CHOICES[i]}: {(emotion*100):.2f}%")
+        st.progress(float(emotion))
+with col2:
+    for i, toxicity in enumerate(toxicitys[0]):
+        st.write(f"{TOXICITY_CHOICES[i]}: {(toxicity*100):.2f}%")
+        st.progress(float(toxicity))
+
+decoded = model.decode(prediction)
+# Display the prediction
+st.write("The predicted emotion is:", decoded[0][0])
+st.write("The predicted toxicity is:", decoded[1][0])

pipeline/model/__init__.py

@@ -0,0 +1,27 @@
+import tensorflow as tf
+
+from tensorflow.keras.models import load_model
+from  transformers import TFBertModel
+
+class MultiTaskModel:
+    """
+    A class used to represent a MultiTaskModel,  which classifies the emotion and toxicity of Valorant chat messages
+    """
+    def __init__(self, is_multilingual = False, preprocessor = None):
+        if is_multilingual:
+            pre_model = TFBertModel.from_pretrained('bert-base-multilingual-cased')
+            self.model = load_model('model_with_bert_multilingual.h5', custom_objects={'TFBertModel': TFBertModel})
+        else:
+            pre_model = TFBertModel.from_pretrained('bert-base-uncased')
+            self.model = load_model('model_with_bert_base.h5', custom_objects={'TFBertModel': pre_model})
+        self.load_preprocess(preprocessor)
+
+    def load_preprocess(self, prep):
+        self.preprocessor = prep
+
+    def predict(self, text):
+        preptext= self.preprocessor.preprocess_text(text)
+        return self.model.predict(preptext)
+    
+    def decode(self, pred):
+        return self.preprocessor.decoder.toxicity(pred[1]), self.preprocessor.decoder.emotion(pred[0])

pipeline/model/model_with_bert_base.py

@@ -0,0 +1,33 @@
+from transformers import TFBertModel
+import tensorflow as tf
+from tensorflow.keras.layers import Input, Dense, LSTM, Bidirectional # type: ignore
+from tensorflow.keras.models import Model # type: ignore
+from tensorflow.keras.optimizers import Adam # type: ignore
+from tensorflow.keras.regularizers import l1_l2 # type: ignore
+
+def build_model(max_length = 65, layer = 40,dropout = 0.69, l2_lstm = 0.01, learning_rate = 1e-4)-> Model:
+    bert = TFBertModel.from_pretrained('bert-base-cased')
+    # Model definition inside the loop
+    input_ids = Input(shape=(max_length,), dtype=tf.int32, name='input_ids')
+    bert_output = bert(input_ids)[0] # type: ignore
+
+    bi_lstm_emotion = Bidirectional(LSTM(layer, dropout=dropout, kernel_regularizer=l1_l2(l2_lstm*0.15,l2_lstm)))(bert_output)
+    bi_lstm_toxicity = Bidirectional(LSTM(layer, dropout=dropout, kernel_regularizer=l1_l2(l2_lstm*0.2,l2_lstm)))(bert_output) # outputs 
+
+    output_emotion = Dense(6, activation='softmax', name='emotion_output')(bi_lstm_emotion)
+    output_toxicity = Dense(7, activation='softmax', name='toxicity_output')(bi_lstm_toxicity)
+
+                        
+    model = Model(inputs=input_ids, outputs=[output_emotion, output_toxicity])
+                    # # Compile
+                    # model = create_multitask_model_with_bert(y_toxicity, y_emotion, TFBertModel, max_length, lstm_dropout=0.2, layers=lstm_layers)
+    model.compile(
+        optimizer=Adam(learning_rate=learning_rate), 
+        loss={'emotion_output': 'categorical_crossentropy', 'toxicity_output': 'categorical_crossentropy'}, 
+        metrics={
+            'emotion_output': ['accuracy', tf.keras.metrics.Precision(name='precision'), tf.keras.metrics.Recall(name='recall'), tf.keras.metrics.AUC(name='em_auc', multi_label=True), tf.keras.metrics.F1Score(name='f1_score')], # type: ignore
+            'toxicity_output': ['accuracy', tf.keras.metrics.Precision(name='precision'), tf.keras.metrics.Recall(name='recall'), tf.keras.metrics.AUC(name='to_auc', multi_label=True), tf.keras.metrics.F1Score(name='f1_score')], # type: ignore
+        }
+    )
+
+    return model

pipeline/model/model_with_bert_multilingual.py

@@ -0,0 +1,10 @@
+from transformers import TFBertModel
+import tensorflow as tf
+from tensorflow.keras.layers import Input, Dense, LSTM, Bidirectional # type: ignore
+from tensorflow.keras.models import Model # type: ignore    
+from tensorflow.keras.optimizers import Adam # type: ignore
+from tensorflow.keras.regularizers import l1_l2 # type: ignore
+
+
+def build_model_multilingual(max_length = 65, layer = 40,dropout = 0.69, l2_lstm = 0.01, learning_rate = 1e-4):
+    

pipeline/preprocessing/__init__.py

@@ -0,0 +1,30 @@
+from transformers import BertTokenizer
+
+class Decoder:
+    def __init__(self):
+        import pickle
+        with open('pipeline/preprocessing/encoder_toxicity.pkl', 'rb') as f:
+            self.__encoder_toxicity = pickle.load(f)
+        with open('pipeline/preprocessing/encoder_emotion.pkl', 'rb') as f:
+            self.__encoder_emotion = pickle.load(f)
+    
+    # Decoding one-hot encoded labels
+    def toxicity(self,pred):
+        return self.__encoder_toxicity.inverse_transform(pred)
+    
+    def emotion(self,pred):
+        return self.__encoder_emotion.inverse_transform(pred)
+
+class Preprocessor:
+    """A class used to represent a Preprocessor, which preprocesses text data for the model"""
+    def __init__(self, is_multilingual = False):
+        if is_multilingual:
+            self.tokenizer = BertTokenizer.from_pretrained('bert-base-multilingual-cased')
+        else:
+            self.tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+        self.decoder = Decoder()
+        """Added a decoder object to the Preprocessor class to decode the one-hot encoded labels"""
+
+    def preprocess_text(self,text):
+        return self.tokenizer.encode(text,add_special_tokens=True, max_length=65,
+        padding="max_length", truncation=True, return_attention_mask=False, return_tensors='tf')

pipeline/preprocessing/encoder_emotion.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba4d4b26a861d6e86d8e0af68999029462ef7370d0dce662624c3567b1fd2eb
+size 660

pipeline/preprocessing/encoder_toxicity.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3bd0fc9b40367e23383e557a1fce50e640e9e7efeee8fbf1faca61a3f12fee9
+size 738

requirements.txt

@@ -0,0 +1,85 @@
+absl-py==2.1.0
+altair==5.3.0
+astunparse==1.6.3
+attrs==23.2.0
+blinker==1.8.2
+cachetools==5.3.3
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+filelock==3.14.0
+flatbuffers==24.3.25
+fsspec==2024.5.0
+gast==0.5.4
+gitdb==4.0.11
+GitPython==3.1.43
+google-auth==2.29.0
+google-auth-oauthlib==1.2.0
+google-pasta==0.2.0
+grpcio==1.63.0
+h5py==3.11.0
+huggingface-hub==0.23.0
+idna==3.7
+Jinja2==3.1.4
+joblib==1.4.2
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+keras==2.15.0
+libclang==18.1.1
+Markdown==3.6
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+ml-dtypes==0.2.0
+namex==0.0.8
+numpy==1.26.4
+oauthlib==3.2.2
+opt-einsum==3.3.0
+optree==0.11.0
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
+protobuf==4.25.3
+pyarrow==16.1.0
+pyasn1==0.6.0
+pyasn1_modules==0.4.0
+pydeck==0.9.1
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.1
+regex==2024.5.15
+requests==2.31.0
+requests-oauthlib==2.0.0
+rich==13.7.1
+rpds-py==0.18.1
+rsa==4.9
+safetensors==0.4.3
+scikit-learn==1.4.2
+scipy==1.13.0
+six==1.16.0
+smmap==5.0.1
+streamlit==1.34.0
+tenacity==8.3.0
+tensorboard==2.15.2
+tensorboard-data-server==0.7.2
+tensorflow==2.15.0
+tensorflow-estimator==2.15.0
+tensorflow-intel==2.15.0
+tensorflow-io-gcs-filesystem==0.31.0
+termcolor==2.4.0
+threadpoolctl==3.5.0
+tokenizers==0.19.1
+toml==0.10.2
+toolz==0.12.1
+tornado==6.4
+tqdm==4.66.4
+transformers==4.41.0
+typing_extensions==4.11.0
+tzdata==2024.1
+urllib3==2.2.1
+watchdog==4.0.0
+Werkzeug==3.0.3
+wrapt==1.14.1