Upload 3 files

app.py

@@ -0,0 +1,289 @@
+import re
+from collections import Counter, defaultdict
+import gradio as gr
+import pandas as pd
+import plotly.graph_objects as go
+import networkx as nx
+import plotly.express as px
+
+def create_recommendation_system(pairs):
+    sets_by_length = defaultdict(list)
+
+    for pair in pairs:
+        sets_by_length[len(pair)].append(set(pair))
+
+    sorted_keys = sorted(sets_by_length.keys(), reverse=True)
+
+    def recommend(restaurant):
+        recommended = set()
+        for length in sorted_keys:
+            for rest_set in sets_by_length[length]:
+                if restaurant in rest_set:
+                    recommended.update(rest_set - {restaurant})
+        return list(recommended)
+
+    return recommend
+
+def recommend(input_string):
+    f = open("task1_output_n_c1_sup4.txt", "r")
+    data = f.read()
+    data = data.split("Frequent Itemsets:")
+
+    clean_string = re.sub(r'\n', '', data[1])
+    pattern = r"\([^\)]+\)"
+
+    extracted_tuples = re.findall(pattern, clean_string.replace("'", ""))
+
+    tuple_list = [tuple(s.strip('()').split(', ')) for s in extracted_tuples]
+
+    recommendation_system = create_recommendation_system(tuple_list)
+
+    output_list = recommendation_system(input_string)
+
+    images_labels = [("https://logowik.com/content/uploads/images/aw-restaurants5299.jpg", "A&W Restaurant"),
+    ("https://inspirebrands.com/wp-content/uploads/2017/10/Arbys.jpg","Arbys"),
+    ("https://www.shutterstock.com/image-vector/vinnytsia-ukraine-october-8-2023-600nw-2372329457.jpg","Burger King"),
+    ("https://static.wixstatic.com/media/cc8696_2f0a91e1d9d245efa98b100adfcdd887~mv2.png/v1/crop/x_0,y_0,w_242,h_71/fill/w_339,h_94,al_c,lg_1,q_85,enc_auto/logo.png","California Kitchen"),
+    ("https://logos-world.net/wp-content/uploads/2022/11/Carls-Jr.-Logo-500x281.png","Carls Jr."),
+    ("https://upload.wikimedia.org/wikipedia/commons/thumb/0/02/Chick-fil-A_Logo.svg/873px-Chick-fil-A_Logo.svg.png","Chick-Fil-A"),
+    ("https://upload.wikimedia.org/wikipedia/en/thumb/3/38/CECLogo2019.svg/330px-CECLogo2019.svg.png","Chuck E. Cheese"),
+    ("https://upload.wikimedia.org/wikipedia/commons/thumb/c/cc/Culver%27s_logo.svg/558px-Culver%27s_logo.svg.png","Culvers"),
+    ("https://upload.wikimedia.org/wikipedia/commons/thumb/a/ae/Dairy_Queen_logo.svg/300px-Dairy_Queen_logo.svg.png", "Dairy Queen"),
+    ("https://logowik.com/content/uploads/images/493_dominospizza.jpg", "Dominos Pizza"),
+    ("https://logos-world.net/wp-content/uploads/2023/03/Five-Guys-Logo-500x281.png", "Five Guys"),
+    ("https://entrackr.com/storage/2023/06/Good-Flippin.jpg", "Good Flippin Burger"),
+    ("https://logowik.com/content/uploads/images/hardees4024.jpg", "Hardees"),
+    ("https://logos-marques.com/wp-content/uploads/2023/04/In-N-Out-Burger-Logo-768x432.png", "In-N-Out"),
+    ("https://logos-world.net/wp-content/uploads/2022/08/Jack-in-the-Box-Logo-500x281.png", "Jack in the Box"),
+    ("https://1000logos.net/wp-content/uploads/2021/05/Jollibee-logo-768x432.png", "Jollibee"),
+    ("https://logowik.com/content/uploads/images/674_kfc.jpg", "KFC"),
+    ("https://visitguernseycounty.com/wp-content/uploads/2022/05/Little-Caesars-Logo-1024x576.jpg", "Little Caesars"),
+    ("https://logowik.com/content/uploads/images/mcdonalds-icon.jpg", "McDonalds"),
+    ("https://images.squarespace-cdn.com/content/v1/53a47e51e4b0e78ae9ed2e97/4b8df8ab-662a-4381-92a6-97839099d5a7/Papa-Johns-logo.jpg", "Papa Johns"),
+    ("https://cdn.nwe.io/files/x/d5/cc/c9810c9ad13188a3e0b2bc6577d7.jpg", "Pizza Inn"),
+    ("https://logowik.com/content/uploads/images/294_pizza_hut_new_logo.jpg", "Pizza hut"),
+    ("https://upload.wikimedia.org/wikipedia/commons/a/a6/PizzaExpress_Logo.jpg", "PizzaExpress"),
+    ("https://images.squarespace-cdn.com/content/v1/53a47e51e4b0e78ae9ed2e97/be0aea01-84cc-4b89-a5e8-314ed394dc3c/Popeyes+logo.jpg", "Popeyes"),
+    ("https://upload.wikimedia.org/wikipedia/commons/d/d9/Original_Round_Table_Pizza_Logo.jpg", "Round Table Pizza"),
+    ("https://logowik.com/content/uploads/images/328_sbarro.jpg", "Sbarro"),
+    ("https://1000logos.net/wp-content/uploads/2023/04/Shake-Shack-Logo-768x432.png", "Shake Shack"),
+    ("https://upload.wikimedia.org/wikipedia/en/thumb/6/6d/Shakey%27s_US_logo.svg/330px-Shakey%27s_US_logo.svg.png", "Shakeys Pizza"),
+    ("https://upload.wikimedia.org/wikipedia/commons/thumb/f/ff/SONIC_New_Logo_2020.svg/1199px-SONIC_New_Logo_2020.svg.png", "Sonic"),
+    ("https://images.getbento.com/accounts/236fb3743b9522eafb90c6d2d20b8115/media/accounts/media/V1G5LTCrSDqyixbNUDpr_logo-tasty-burger.png", "Tasty burger"),
+    ("https://cdn.worldvectorlogo.com/logos/uno-pizzeria.svg", "Uno Pizzeria"),
+    ("https://upload.wikimedia.org/wikipedia/commons/thumb/2/28/Wahlburgers_Logo.svg/768px-Wahlburgers_Logo.svg.png", "Wahlburgers"),
+    ("https://logowik.com/content/uploads/images/866_wendys.jpg", "Wendys"),
+    ("https://logowik.com/content/uploads/images/whataburger8433.jpg", "Whataburger"),
+    ("https://encrypted-tbn2.gstatic.com/images?q=tbn:ANd9GcTsUZPMFzUmACfaeSrMSZsgGn5gnbXNyYRPxIrS1PfCrFWI9QJhrlkmdG9IhFbi", "White Castle")]
+
+    output = []
+    for i in images_labels:
+        if(i[1] in output_list):
+          output.append(i)
+
+    return output
+
+
+def plot_heatmap():
+  f = open("task1_output_n_c1_sup4.txt", "r")
+  data = f.read()
+  data = data.split("Frequent Itemsets:")
+
+  clean_string = re.sub(r'\n', '', data[1])
+  pattern = r"\([^\)]+\)"
+
+  extracted_tuples = re.findall(pattern, clean_string.replace("'", ""))
+
+  frequent_itemsets = [tuple(s.strip('()').split(', ')) for s in extracted_tuples]
+  
+
+  # Initialize a defaultdict for item pair frequencies
+  pair_counts = defaultdict(int)
+
+  # Count frequencies of item pairs, excluding self-pairings
+  for itemset in frequent_itemsets:
+      unique_items = list(set(itemset))
+      for i in range(len(unique_items)):
+          for j in range(i + 1, len(unique_items)):
+              pair = tuple(sorted([unique_items[i], unique_items[j]]))
+              pair_counts[pair] += 1
+
+  # Get a sorted list of unique items
+  all_items = sorted(set(item for pair in pair_counts for item in pair))
+
+  # Create a DataFrame for the heatmap
+  heatmap_data = pd.DataFrame(0, index=all_items, columns=all_items)
+  for (item1, item2), count in pair_counts.items():
+      heatmap_data.at[item1, item2] = count
+      heatmap_data.at[item2, item1] = count  # Ensure symmetry
+
+  # Create the heatmap
+  fig = px.imshow(heatmap_data, labels=dict(x="Item", y="Item", color="Frequency"),
+                  x=all_items, y=all_items,
+                  color_continuous_scale=px.colors.sequential.Blues)
+
+  fig.update_layout(title='Heatmap of Item Co-occurrences (Excluding Self-Pairings)',
+                    title_x=0.5)
+
+  return fig
+
+def plot_bar():
+  f = open("task1_output_n_c1_sup4.txt", "r")
+  data = f.read()
+  data = data.split("Frequent Itemsets:")
+
+  clean_string = re.sub(r'\n', '', data[1])
+  pattern = r"\([^\)]+\)"
+
+  extracted_tuples = re.findall(pattern, clean_string.replace("'", ""))
+
+  frequent_itemsets = [tuple(s.strip('()').split(', ')) for s in extracted_tuples]
+
+  # Flatten the list of itemsets and count occurrences of each item
+  items = [item for itemset in frequent_itemsets for item in itemset]
+  item_counts = Counter(items)
+
+  # Convert the counter to a DataFrame
+  df = pd.DataFrame(item_counts.items(), columns=['Item', 'Count'])
+
+  # Sort the DataFrame in descending order by 'Count'
+  df = df.sort_values(by='Count', ascending=False)
+
+  # Create the bar chart
+  fig = px.bar(df, x='Item', y='Count', title='Frequency of Items in Frequent Itemsets',
+              labels={'Count': 'Frequency'}, color='Count', height=600)
+
+  fig.update_layout(xaxis_title='Item', yaxis_title='Frequency', title_x=0.5)
+
+  return fig
+
+def plot_association():
+  f = open("task1_output_n_c1_sup4.txt", "r")
+  data = f.read()
+  data = data.split("Frequent Itemsets:")
+
+  clean_string = re.sub(r'\n', '', data[1])
+  pattern = r"\([^\)]+\)"
+
+  extracted_tuples = re.findall(pattern, clean_string.replace("'", ""))
+
+  frequent_itemsets = [tuple(s.strip('()').split(', ')) for s in extracted_tuples]
+
+  G = nx.DiGraph()
+
+  for itemset in frequent_itemsets:
+      if len(itemset) == 2:
+          G.add_edge(itemset[0], itemset[1])
+      else:
+          for i in range(len(itemset)):
+              for j in range(i + 1, len(itemset)):
+                  G.add_edge(itemset[i], itemset[j])
+
+  pos = nx.spring_layout(G)
+
+  edge_x = []
+  edge_y = []
+  for edge in G.edges():
+      x0, y0 = pos[edge[0]]
+      x1, y1 = pos[edge[1]]
+      edge_x.append(x0)
+      edge_x.append(x1)
+      edge_x.append(None)
+      edge_y.append(y0)
+      edge_y.append(y1)
+      edge_y.append(None)
+
+  edge_trace = go.Scatter(
+      x=edge_x, y=edge_y,
+      line=dict(width=0.5, color='#888'),
+      hoverinfo='none',
+      mode='lines')
+
+  node_x = []
+  node_y = []
+  for node in G.nodes():
+      x, y = pos[node]
+      node_x.append(x)
+      node_y.append(y)
+
+  node_trace = go.Scatter(
+      x=node_x, y=node_y,
+      mode='markers+text',
+      text=[node for node in G.nodes()],
+      textposition="top center",
+      hoverinfo='text',
+      marker=dict(
+          showscale=True,
+          colorscale='YlGnBu',
+          size=10,
+          colorbar=dict(
+              thickness=15,
+              title='Node Connections',
+              xanchor='left',
+              titleside='right'
+          ),
+          line_width=2))
+
+  fig = go.Figure(data=[edge_trace, node_trace],
+              layout=go.Layout(
+                  title='<br>Association Rule Graph',
+                  titlefont_size=16,
+                  showlegend=False,
+                  hovermode='closest',
+                  margin=dict(b=20,l=5,r=5,t=40),
+                  annotations=[ dict(
+                      text="Association Rule Network",
+                      showarrow=False,
+                      xref="paper", yref="paper",
+                      x=0.005, y=-0.002 ) ],
+                  xaxis=dict(showgrid=False, zeroline=False),
+                  yaxis=dict(showgrid=False, zeroline=False))
+                  )
+  return fig
+
+sorted_unique_restaurants = [
+ 'A&W Restaurant',
+ 'Arbys',
+ 'Burger King',
+ 'California Kitchen',
+ 'Carls Jr.',
+ 'Chick-Fil-A',
+ 'Chuck E. Cheese',
+ 'Culvers',
+ 'Dairy Queen',
+ 'Dominos Pizza',
+ 'Five Guys',
+ 'Good Flippin Burger',
+ 'Hardees',
+ 'In-N-Out',
+ 'Jack in the Box',
+ 'Jollibee',
+ 'KFC',
+ 'Little Caesars',
+ 'McDonalds',
+ 'Papa Johns',
+ 'Pizza Inn',
+ 'Pizza hut',
+ 'PizzaExpress',
+ 'Popeyes',
+ 'Round Table Pizza',
+ 'Sbarro',
+ 'Shake Shack',
+ 'Shakeys Pizza',
+ 'Sonic',
+ 'Tasty burger',
+ 'Uno Pizzeria',
+ 'Wahlburgers',
+ 'Wendys',
+ 'Whataburger',
+ 'White Castle']
+
+recommender = gr.Interface(fn=recommend, inputs=gr.Dropdown(choices=sorted_unique_restaurants, value="Burger King"), outputs=gr.Gallery(label="Generated images", show_label=False, elem_id="gallery", columns=[4], object_fit="contain", height="auto"), title='Restaurant Recommender System', description='Find your ideal restaurant')  
+vizz_heatmap = gr.Interface(fn=plot_heatmap, inputs = None, outputs=gr.Plot(label="Heatmap"), description = "Restaurant Itemset Frequency")
+vizz_bar = gr.Interface(fn=plot_bar, inputs = None, outputs=gr.Plot(label="Bar Graph"), description = "Restaurant Frequency")
+vizz_graph = gr.Interface(fn=plot_association, inputs = None, outputs=gr.Plot(label="Association Graph"), description = "Association Graph of Restaurants")
+
+
+tabbed = gr.TabbedInterface([recommender, vizz_heatmap, vizz_bar, vizz_graph], ["Restaurant Recommender", "Heatmap", "Restaurant Frequency", "Association Graph"])
+
+tabbed.queue().launch(share = True, debug = True)

requirements.txt

@@ -0,0 +1,2 @@
+plotly==5.15.0
+networkx==3.3