Update emotion_recognition_fine_tuning.py

emotion_recognition_fine_tuning.py

@@ -7,192 +7,6 @@ Original file is located at
     https://colab.research.google.com/drive/1pZgt5n6943GB5oq_h43LjAYoA4yi-EST
 """
 
-!pip install datasets
-
-from datasets import load_dataset
-
-dataset = load_dataset("dair-ai/emotion")
-
-import pandas as pd
-df_train=pd.DataFrame(dataset["train"])
-df_train.head()
-
-# @title label
-
-from matplotlib import pyplot as plt
-df_train['label'].plot(kind='hist', bins=20, title='label')
-# plt.gca().spines[['top', 'right',]].set_visible(False)
-
-df_test=pd.DataFrame(dataset["test"])
-df_test.head()
-
-# @title label
-
-from matplotlib import pyplot as plt
-df_test['label'].plot(kind='hist', bins=20, title='label')
-plt.gca().spines[['top', 'right',]].set_visible(False)
-
-dataset.keys()
-
-df_valid=pd.DataFrame(dataset["validation"])
-df_valid.head()
-
-df_train.info()
-
-import numpy as np
-
-train_label=np.array(df_train.label)
-test_label=np.array(df_test.label)
-valid_label=np.array(df_valid.label)
-
-# Assuming df_train.text is a Pandas Series
-train_text = df_train.text.tolist()
-test_text = df_test.text.tolist()
-valid_text = df_valid.text.tolist()
-
-# @title Label Value Distribution
-
-df_valid['label'].value_counts().plot(kind='bar')
-
-print(df_train.shape)
-print(df_test.shape)
-print(df_valid.shape)
-
-labels={0:"sadness",1:"joy",2:"love",3:"anger",4:"fear",5:"surprise"}
-labels2={"sadness":0,"joy":1,"love":2,"anger":3,"fear":4,"surprise":5}
-
-from tensorflow.keras.utils import to_categorical
-one_hot_train_labels = to_categorical(df_train.label)
-one_hot_valid_labels = to_categorical(df_valid.label)
-one_hot_train_labels
-
-import tensorflow as tf
-# Reshape the labels to match the model's output shape
-one_hot_train_labels = tf.reshape(one_hot_train_labels, (-1, 2))
-one_hot_valid_labels = tf.reshape(one_hot_valid_labels, (-1, 2))
-one_hot_train_labels
-
-from transformers import AutoTokenizer
-
-tokenizer = AutoTokenizer.from_pretrained("google-bert/bert-base-uncased")
-tokenized_data_train = tokenizer(train_text, return_tensors="np", padding=True)
-tokenized_data_valid = tokenizer(valid_text, return_tensors="np", padding=True)
-
-
-
-train_label.shape
-
-# Tokenizer returns a BatchEncoding, but we convert that to a dict for Keras
-tokenized_data_train = dict(tokenized_data_train)
-tokenized_data_valid = dict(tokenized_data_valid)
-
-# labels = np.array(dataset["label"])
-
-from transformers import TFAutoModelForSequenceClassification, AutoTokenizer
-import tensorflow as tf
-
-# Load pre-trained BERT model
-model = TFAutoModelForSequenceClassification.from_pretrained("google-bert/bert-base-uncased",num_labels=6, ignore_mismatched_sizes=True)
-
-
-
-model.layers[0].trainable=False
-
-for layer in model.layers:
-    print(layer)
-
-model.layers
-
-from transformers import AutoConfig
-
-# Load pre-trained BERT model
-# model = TFAutoModelForSequenceClassification.from_pretrained("SamLowe/roberta-base-go_emotions")
-
-# Load model configuration
-# config = AutoConfig.from_pretrained("SamLowe/roberta-base-go_emotions")
-
-# Define the number of classes in your downstream task
-num_classes_downstream = 6  # Replace with the actual number of classes in your task
-
-# Replace the classifier layer with a new one for your task
-# model.config.num_labels = num_classes_downstream
-model.classifier = tf.keras.layers.Dense(num_classes_downstream, activation='softmax')
-
-# Continue with fine-tuning and model compilation
-
-model.classifier
-
-model.summary()
-
-model.config.id2label=labels
-model.config.label2id=labels2
-
-model.logits
-
-# Compile the model with the optimizer and loss function
-model.compile(optimizer="Adam",metrics=["accuracy"])
-
-# Assuming tokenized_data_train, train_label, tokenized_data_valid, and valid_label are defined
-model.fit(tokenized_data_train, train_label, epochs=30, validation_data=(tokenized_data_valid, valid_label))
-
-val=tokenizer(["hello boys I am good"],padding=True,return_tensors="np")
-
-import tensorflow as tf
-
-# Assuming 'val' is your input data
-predictions = loaded_model.predict(val)
-
-# Extract logits from predictions
-logits = predictions[0]  # Assuming logits are the first element in the tuple
-
-# Apply softmax using tf.nn.softmax
-probabilities = tf.nn.softmax(logits)
-
-# Now 'probabilities' contains the softmax probabilities
-print(probabilities.numpy())
-
-model.save_pretrained("/content/sample_data/emotion_model_dhruv")
-
-from google.colab import files
-
-# Specify the file path
-file_path = '/content/sample_data/emotion_model_dhruv'  # Adjust the file path accordingly
-
-# Download the file
-files.download(file_path)
-
-import shutil
-
-# Specify the directory to be copied
-directory_to_copy = '/content/sample_data/emotion_model_dhruv'  # Adjust the directory path accordingly
-
-# Specify the destination directory in Google Drive
-destination_directory = '/content/drive/My Drive/'
-
-# Copy the directory to Google Drive
-shutil.copytree(directory_to_copy, os.path.join(destination_directory, os.path.basename(directory_to_copy)))
-
-from transformers import TFBertForSequenceClassification
-
-# Load the fine-tuned model from the saved directory
-loaded_model = TFBertForSequenceClassification.from_pretrained("/content/sample_data/emotion_model_dhruv")
-
-my=dict(tokenizer(["hello boys I am good"],padding=True,return_tensors="np"))
-my
-
-# Assuming my['input_ids'], my['token_type_ids'], and my['attention_mask'] are your input tensors
-input_ids = my['input_ids']
-token_type_ids = my['token_type_ids']
-attention_mask = my['attention_mask']
-
-# Make predictions using the loaded model, setting verbose=0 or verbose=1
-# predictions = loaded_model.predict([input_ids, token_type_ids, attention_mask], verbose=0)
-# or
-predictions = loaded_model.predict([input_ids, token_type_ids, attention_mask], verbose=1)
-
-my['input_ids'] = np.array(my['input_ids'])
-my['token_type_ids'] = np.array(my['token_type_ids'])
-my['attention_mask'] = np.array(my['attention_mask'])
 
 """Our Application"""
 
@@ -203,7 +17,7 @@ import numpy as np
 import tensorflow as tf # Apply softmax using tf.nn.softmax
 
 # Load the fine-tuned model from the saved directory
-loaded_model = TFBertForSequenceClassification.from_pretrained("/content/drive/MyDrive/emotion_model_dhruv")
+loaded_model = TFBertForSequenceClassification.from_pretrained("emotion_model_dhruv")
 loaded_tokenizer=AutoTokenizer.from_pretrained("google-bert/bert-base-uncased")
 
 def predict_emotion(text):
@@ -226,5 +40,5 @@ my_labels=["sadness","joy","love","anger","fear","surprise"]
 import gradio as gr
 inputs = gr.Textbox(lines=1, label="Input Text")
 outputs = gr.Label(num_top_classes=6)
-interface = gr.Interface(fn=predict_emotion, inputs=inputs, outputs=outputs)
+interface = gr.Interface(fn=predict_emotion, inputs=inputs, outputs=outputs,title="Emotion Recognition in Text - NLP")
 interface.launch()