app

.gitattributes

@@ -1,34 +1,3 @@
-*.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
-*.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
+# Auto detect text files and perform LF normalization
+* text=auto
+model/cnn_model.h5 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,91 @@
+import gradio
+import keras
+import nltk
+import numpy as np
+import pandas as pd
+from keras.preprocessing.text import Tokenizer
+from keras.utils import pad_sequences
+from nltk.corpus import stopwords
+from nltk.stem import PorterStemmer
+
+nltk.download("stopwords")
+import re
+
+vocab_size = 25000
+embedding_dim = 64
+max_length = 50
+trunc_type = 'pre'
+padding_type = 'pre'
+oov_tok = '<OOV>'
+
+labels = {
+    1: 'admiration',
+    2: 'anger',
+    3: 'curiosity',
+    4: 'disappointment',
+    5: 'disgust',
+    6: 'embarrassment',
+    7: 'excitement',
+    8: 'fear',
+    9: 'gratitude',
+    10: 'love',
+    11: 'nervousness',
+    12: 'pride',
+    13: 'sadness',
+    14: 'neutral'
+}
+
+
+def get_tokenizer():
+    df = pd.read_csv('emo/util/temp.csv', ).reset_index(drop=True)
+    X = df['text']
+    tokenizer = Tokenizer(num_words=vocab_size, oov_token=oov_tok)
+    tokenizer.fit_on_texts(X)
+    return tokenizer
+
+
+def clean_text(text):
+    stemmer = PorterStemmer()
+    stp_words = set(stopwords.words('english'))
+    sent = text.replace("NAME", "")
+    sent = re.sub('[^a-zA-Z]', " ", sent)
+    sent = sent.lower()
+    sent = sent.split()
+    sent = [stemmer.stem(words) for words in sent if words not in stp_words]
+    text = [' '.join(sent)]
+    # print(text)
+    # print((sent))
+
+    train_seq = get_tokenizer().texts_to_sequences(text)
+    # print(train_seq)
+    test_padding = pad_sequences(train_seq, max_length, padding=padding_type, truncating=trunc_type)
+
+    return test_padding
+
+
+def predict(text):
+    model = keras.models.load_model('emo/model/cnn_model.h5')
+    pred = model.predict(text)
+    pred_class = np.argmax(pred, axis=-1)
+    return labels.get(pred_class[0])
+
+
+def my_inference_function(text):
+    # TODO: do the pre-processing of text to be able to feed it
+    #  in the model
+    # 1. Preprocess
+    inp = clean_text(text)
+    return predict(inp)
+
+
+gradio_interface = gradio.Interface(
+    fn=my_inference_function,
+    inputs="text",
+    outputs="text",
+    # outputs=gradio.outputs.Label(num_top_classes=5),
+    title='Emotion Classification',
+    description=f"Let's know how you feel!!!",
+    allow_flagging="never"
+)
+
+gradio_interface.launch(inbrowser=True)

model/cnn_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c5db9470765f2949fa8880a82b18e7a9eca262dea57357d0a4b1251fe5f7bb
+size 20204520

requirements.txt

@@ -0,0 +1,6 @@
+gradio==3.32.0
+keras~=2.11.0
+
+nltk~=3.8.1
+numpy~=1.21.6
+pandas~=1.3.5