Upload main.py

main.py

@@ -0,0 +1,83 @@
+from fastapi import FastAPI
+from sklearn.model_selection import train_test_split
+from request_body import request_body
+from utilities import *
+from classifier import Classifier
+
+# Download necessary modules
+nltk.download('punkt')
+
+# Get dataset and convert it into suitable form of input for the classification model
+filename = "airline_sentiment_analysis.csv"
+raw_data = get_data_for_training(filename)
+sentences, labels = get_data_and_labels(raw_data)
+sentences = get_word_embeddings(sentences)
+
+# Spliting the dataset into Training and Testing dataset to train the model
+# Train Set = 50%
+# Test Set = 50%
+airline_train_data, airline_test_data, airline_train_labels, airline_test_labels = train_test_split(
+    sentences, labels, test_size=0.5, random_state=42)
+
+# Vectorize the sequence for both train and test datasets
+x_train = vectorize_sequence(airline_train_data, 20000)
+x_test = vectorize_sequence(airline_test_data, 20000)
+
+y_train = np.asarray(airline_train_labels).astype('float32')
+y_test = np.asarray(airline_test_labels).astype('float32')
+
+print(x_train.shape)
+print(x_test.shape)
+print(y_train.shape)
+print(y_test.shape)
+
+# # Naive Bayes
+# classifier_mnb = Classifier("Naive Bayes")
+# classifier_mnb.train(x_train, y_train)
+# print("NAIVE BAYES")
+# print("train shape: " + str(x_train.shape))
+# print("score on test: " + str(classifier_mnb.score(x_test, y_test)))
+# print("score on train: " + str(classifier_mnb.score(x_train, y_train)))
+
+# Logistic Regression
+classifier_lr = Classifier("Logistic Regression")
+classifier_lr.train(x_train, y_train)
+print("LOGISTIC REGRESSION")
+print("train shape: " + str(x_train.shape))
+print("score on test: " + str(classifier_lr.score(x_test, y_test)))
+print("score on train: " + str(classifier_lr.score(x_train, y_train)))
+
+# # KNN
+# classifier_knn = Classifier("KNN")
+# classifier_knn.train(x_train, y_train)
+
+# print("KNN")
+# print("train shape: " + str(x_train.shape))
+# print("score on train: " + str(classifier_knn.score(x_train, y_train)))
+# print("score on test: " + str(classifier_knn.score(x_test, y_test)))
+
+# # Support Vector Machines
+# classifier_svm = Classifier("SVM")
+# classifier_svm.train(x_train, y_train)
+
+# print("SUPPORT VECTOR MACHINE")
+# print("train shape: " + str(x_train.shape))
+# print("score on test: " + str(classifier_svm.score(x_test, y_test)))
+# print("score on train: " + str(classifier_svm.score(x_train, y_train)))
+
+app = FastAPI()
+
+@app.post('/predict')
+def predict(data: request_body):
+    text = data.text
+    sequence = get_sequence(text)
+    sequence = vectorize_sequence(sequence, 20000)
+    print(sequence)
+
+    class_idx = classifier_lr.classify(sequence)[0]
+    print(class_idx)
+    class_idx = (int)(class_idx)
+    if class_idx==1:
+        return {'sentiment': "positive"}
+    else:
+        return {'sentiment': "negative"}