Modified demo, master_file, index,htnl

Demo.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -37,44 +37,42 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
     "#Importing Models:\n",
     "from joblib import load\n",
-    "dt_clf = load(filename=\"Trained_models\\Decision_tree_tfid.joblib\")\n",
-    "rf_clf = load(filename=\"Trained_models\\Random_forest_tfid_100_trees.joblib\")\n",
-    "nb_clf = load(filename=\"Trained_models\\ComplimentNB_tfid.joblib\")\n",
-    "svm_clf = load(filename=\"Trained_models\\SVM_linear_kernel_tfid.joblib\")\n",
-    "perc_clf = load(filename=\"Trained_models\\Perceptron_tfid.joblib\")\n",
-    "lr_clf = load(filename=\"Trained_models\\Logistic_regression_tfid.joblib\")"
+    "dt_clf = load(filename=\"webapp/Trained_models/Decision_tree_tfid.joblib\")\n",
+    "rf_clf = load(filename=\"webapp/Trained_models/Random_forest_tfid_100_trees.joblib\")\n",
+    "nb_clf = load(filename=\"webapp/Trained_models/ComplimentNB_tfid.joblib\")\n",
+    "svm_clf = load(filename=\"webapp/Trained_models/SVM_linear_kernel_tfid.joblib\")\n",
+    "perc_clf = load(filename=\"webapp/Trained_models/Perceptron_tfid.joblib\")\n",
+    "lr_clf = load(filename=\"webapp/Trained_models/Logistic_regression_tfid.joblib\")\n",
+    "vectorizer = load(filename=\"webapp/Trained_models/Vectorizer.joblib\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
     "from nltk.stem import PorterStemmer\n",
     "import re\n",
     "\n",
     "def stem_text(txt_input):\n",
-    "    # Initialize Porter Stemmer\n",
+    "\n",
+    "    #Apply stemming to input text:\n",
     "    stemmer = PorterStemmer()\n",
-    "    \n",
     "    txt_series = pd.Series(txt_input)\n",
-    "    # Apply stemming to each word in the input text\n",
     "    stemmed_txt = txt_series.apply(lambda x: ' '.join([stemmer.stem(word) for word in x.split()]))\n",
-    "    \n",
+    "\n",
     "    return stemmed_txt\n",
     "\n",
     "def preprocess_input(text, age, time_of_tweet):\n",
-    "    # Remove special characters, numbers, and other punctuations\n",
+    "\n",
     "    processed_text = text.replace(\"[^a-zA-Z#]\", \" \")\n",
-    "    \n",
-    "    # Convert processed text to lowercase\n",
     "    processed_text = processed_text.lower()\n",
     "    \n",
     "    # Apply Porter stemming\n",
@@ -88,7 +86,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -129,31 +127,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
-    "vectorizer = load(filename=\"Trained_models\\Vectorizer.joblib\")\n",
-    "\n",
     "def predict_label(text, age, time_of_tweet):\n",
-    "    # Preprocess input\n",
+    "\n",
     "    processed_data = preprocess_input(text, age, time_of_tweet)\n",
     "    \n",
     "    # Vectorize the processed text\n",
     "    vectorized_input = vectorizer.transform(processed_data['processed_text'])\n",
     "    \n",
     "    # Concatenate the age and time_of_tweet features with the vectorized text\n",
     "    X_input = sparse.hstack([processed_data[['age', 'time_of_tweet']], vectorized_input])\n",
-    "\n",
-    "    # Make predictions using the AdaBoost classifier\n",
+    "    \n",
     "    predictions = ensemble_predict(X_input, dt_clf, rf_clf, nb_clf, svm_clf, perc_clf, lr_clf)\n",
     "    \n",
     "    return predictions"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {