Pri mistake

backend/app.py

@@ -1,46 +1,113 @@
 import json
 import os
-from flask import Flask, render_template, request
+from flask import Flask, render_template, request, jsonify
 from flask_cors import CORS
-from helpers.MySQLDatabaseHandler import MySQLDatabaseHandler
-import pandas as pd
+import re
+from collections import defaultdict
+import math
 
-# ROOT_PATH for linking with all your files. 
-# Feel free to use a config.py or settings.py with a global export variable
-os.environ['ROOT_PATH'] = os.path.abspath(os.path.join("..",os.curdir))
+app = Flask(__name__)
+CORS(app)
+
+# ROOT_PATH for linking with all your files.
+os.environ['ROOT_PATH'] = os.path.abspath(os.path.join("..", os.curdir))
 
 # Get the directory of the current script
 current_directory = os.path.dirname(os.path.abspath(__file__))
 
 # Specify the path to the JSON file relative to the current script
-json_file_path = os.path.join(current_directory, 'init.json')
+json_file_path = os.path.join(current_directory, 'data.json')
 
-# Assuming your JSON data is stored in a file named 'init.json'
+# Assuming your JSON data is stored in a file named 'data.json'
 with open(json_file_path, 'r') as file:
     data = json.load(file)
-    episodes_df = pd.DataFrame(data['episodes'])
-    reviews_df = pd.DataFrame(data['reviews'])
 
-app = Flask(__name__)
-CORS(app)
+def preprocess_data(data):
+    preprocessed_data = defaultdict(str)
+    for city, categories in data.items():
+        for _, details in categories.items():
+            food_info = details.get('Eat')
+            if food_info is not None:
+                preprocessed_data[city] = food_info
+    return preprocessed_data
+
+def create_term_frequency_matrix(data):
+    term_frequency_matrix = defaultdict(dict)
+    for city, food_info in data.items():
+        terms = re.findall(r'\w+', food_info.lower())
+        for term in terms:
+            if term not in term_frequency_matrix[city]:
+                term_frequency_matrix[city][term] = 1
+            else:
+                term_frequency_matrix[city][term] += 1
+    return term_frequency_matrix
+
+def calculate_jaccard_similarity(query, data_term_frequency_matrix):
+    query_terms = set(re.findall(r'\w+', query.lower()))
+    similarities = {}
+    for city, matrix in data_term_frequency_matrix.items():
+        data_terms = set(matrix.keys())
+        intersection = query_terms.intersection(data_terms)
+        union = query_terms.union(data_terms)
+        jaccard_similarity = len(intersection) / len(union)
+        similarities[city] = jaccard_similarity
+    return similarities
+
+def top_sim(similarities):
+    sorted_similarities = sorted(similarities.items(), key=lambda x: x[1], reverse=True)
+    top_10 = sorted_similarities[:10]
+    return top_10
 
-# Sample search using json with pandas
-def json_search(query):
-    matches = []
-    merged_df = pd.merge(episodes_df, reviews_df, left_on='id', right_on='id', how='inner')
-    matches = merged_df[merged_df['title'].str.lower().str.contains(query.lower())]
-    matches_filtered = matches[['title', 'descr', 'imdb_rating']]
-    matches_filtered_json = matches_filtered.to_json(orient='records')
-    return matches_filtered_json
+def calculate_query_vector(query, data_term_frequency_matrix):
+    query_vector = defaultdict(int)
+    terms = re.findall(r'\w+', query.lower())
+    for term in terms:
+        query_vector[term] += 1
+    return query_vector
+
+def calculate_cosine_similarity(query_vector, doc_vector):
+    dotprod = 0
+    for term in query_vector:
+        prod = query_vector.get(term,0)*doc_vector.get(term,0)
+        dotprod+=prod
+    query_sum = 0
+    doc_sum = 0
+    for value in query_vector.values():
+        query_sum += (value**2)
+    for value in query_vector.values():
+        doc_sum += (value**2)
+
+    query_norm = math.sqrt(query_sum)
+    doc_norm = math.sqrt(doc_sum)
+
+    if query_norm==0 or doc_norm==0:
+        return 0
+    cossim = dotprod / (query_norm*doc_norm)
+    return cossim
 
 @app.route("/")
 def home():
-    return render_template('base.html',title="sample html")
+    return render_template('base.html', title="Sample HTML")
+
+@app.route("/food_search")
+def food_search():
+    query = request.args.get("query")
+    preprocessed_data = preprocess_data(data)
+    term_frequency_matrix = create_term_frequency_matrix(preprocessed_data)
+    # similarities = calculate_jaccard_similarity(query, term_frequency_matrix)
+
+    query_vector = calculate_query_vector(query, term_frequency_matrix)
+    similarities = {}
+    for city, city_vector in term_frequency_matrix.items():
+        cosine_sim = calculate_cosine_similarity(query_vector, city_vector)
+        similarities[city] = cosine_sim
+
+
+    top_10 = top_sim(similarities)
+
+    top_10_json = [{"city": city, "similarity": similarity} for city, similarity in top_10]
+    return jsonify(top_10=top_10_json)
 
-@app.route("/episodes")
-def episodes_search():
-    text = request.args.get("title")
-    return json_search(text)
 
-if 'DB_NAME' not in os.environ:
-    app.run(debug=True,host="0.0.0.0",port=5000)
+if __name__ == "__main__":
+    app.run(debug=True)

backend/static/style.css

@@ -1,91 +1,124 @@
-.full-body-container{
+.full-body-container {
     position: absolute;
-    top:0;
-    left:0;
-    right:0;
-    bottom:0;
-    width:100%;
-    height:100%;
+    top: 0;
+    left: 0;
+    right: 0;
+    bottom: 0;
+    width: 100%;
+    height: 100%;
     display: flex;
     justify-content: start;
     align-items: center;
     flex-direction: column;
 }
 
-#google-c{
-    color:#4285F4;
+#google-0 {
+    color: #DB4437; /* A */
+}
+
+#google-1 {
+    color: #4285F4; /* b */
+}
+
+#google-2 {
+    color: #0F9D58; /* r */
+}
+
+#google-3 {
+    color: #F4B400; /* o */
+}
+
+#google-4 {
+    color: #4285F4; /* a */
+}
+
+#google-5 {
+    color: #DB4437; /* d */
+}
+
+#google-6 {
+    color
+    : #0F9D58; /* A */
+}
+
+#google-7 {
+    color: #DB4437; /* d */
+}
+
+#google-8 {
+    color: #F4B400; /* v */
 }
 
-#google-s{
-    color:#DB4437;
+#google-9 {
+    color: #4285F4; /* i */
 }
 
-#google-4{
-    color:	#F4B400;
+#google-10 {
+    color: #DB4437; /* s */
 }
 
-#google-3{
-    color:	#4285F4;
+#google-11 {
+    color: #0F9D58; /* e */
 }
 
-#google-0-1{
-    color:	#0F9D58;
+#google-12 {
+    color: #F4B400; /* r */
 }
 
-#google-0-2{
-    color:#DB4437;
+#google-13 {
+    color: #4285F4; /* s */
 }
 
-.google-colors{
+.google-colors {
     display: flex;
     align-items: center;
     font-size: 48px;
     font-family: 'Open Sans', sans-serif;
 }
 
-.google-colors h1{
+.google-colors h1 {
     margin-bottom: 0;
     margin-right: 3px;
 }
 
-.input-box{
+.input-box {
     border-radius: 50px;
-    border:1px solid black;
+    border: 1px solid black;
     display: flex;
     align-items: center;
     margin-top: 10px;
-    padding:12px;
+    padding: 12px;
     width: 600px;
 }
 
-.input-box img{
+.input-box img {
     height: 20px;
-    width:20px;
+    width: 20px;
 }
 
-.top-text{
+.top-text {
     display: flex;
     flex-direction: column;
     align-items: center;
 }
 
-.input-box input{
+.input-box input {
     width: 100%;
     margin-left: 10px;
     font-size: 16px;
     border: none;
     outline: 0;
 }
 
-#answer-box{
+#answer-box {
     width: 700px;
-    margin-top:50px; 
+    margin-top: 50px;
 }
 
-.episode-title{
+.episode-title {
     font-family: 'Kanit', sans-serif;
 }
 
-.episode-desc{
+.episode-desc {
     font-family: 'Montserrat', sans-serif;
 }