changes

airbnb.ipynb

@@ -337,56 +337,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 213,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "c:\\Users\\ardit\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\gradio\\deprecation.py:43: UserWarning: You have unused kwarg parameters in Slider, please remove them: {'step_size': 100}\n",
-      "  warnings.warn(\n",
-      "c:\\Users\\ardit\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\gradio\\deprecation.py:43: UserWarning: You have unused kwarg parameters in Radio, please remove them: {'multiselect': False}\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Running on local URL:  http://127.0.0.1:7901\n",
-      "\n",
-      "To create a public link, set `share=True` in `launch()`.\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div><iframe src=\"http://127.0.0.1:7901/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
-      ],
-      "text/plain": [
-       "<IPython.core.display.HTML object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/plain": []
-     },
-     "execution_count": 213,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[[700, 45, 'Queens', 'I want to take a break from work 😴!!!']]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import gradio as gr\n",
     "import statistics\n",
@@ -459,6 +412,171 @@
     "    btn.click(predict, [input1, input2, input3, input4], [output1, output2])\n",
     "demo.launch(share=False)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.system('pip install openpyxl')\n",
+    "os.system('pip install sentence-transformers')\n",
+    "import pandas as pd\n",
+    "import gradio as gr\n",
+    "import statistics\n",
+    "from sklearn.neighbors import NearestNeighbors\n",
+    "from sentence_transformers import SentenceTransformer\n",
+    "\n",
+    "df = pd.read_parquet('df_encoded.parquet')\n",
+    "df['neighbourhood group'][0:2500] = df['neighbourhood group'][0:2500].apply(lambda x : 'Manhattan')\n",
+    "df['neighbourhood group'][2500:5000] = df['neighbourhood group'][0:2500].apply(lambda x : 'Brooklyn')\n",
+    "df['neighbourhood group'][5000:7500] = df['neighbourhood group'][0:2500].apply(lambda x : 'Queens')\n",
+    "df['neighbourhood group'][7500:] = df['neighbourhood group'][0:2500].apply(lambda x : 'Bronx')\n",
+    "df['location'] = df['neighbourhood group']\n",
+    "df = df[['price', 'sq. meters', 'description', 'location', 'host name', 'cancellation_policy', 'house_rules', 'text_vector_']]\n",
+    "df = df.reset_index(drop=True)\n",
+    "df\n",
+    "\n",
+    "model = SentenceTransformer('all-mpnet-base-v2') #all-MiniLM-L6-v2 #all-mpnet-base-v2\n",
+    "\n",
+    "#prepare model #we run it anew in the search function every time, after the initial filtering\n",
+    "# nbrs = NearestNeighbors(n_neighbors=3, algorithm='ball_tree').fit(df['text_vector_'].values.tolist())\n",
+    "\n",
+    "def closest_number(x):\n",
+    "    closest_numbers = [25, 40, 45, 55, 60, 70]\n",
+    "    closest_number = closest_numbers[0]\n",
+    "    min_distance = abs(x - closest_number)\n",
+    "    for number in closest_numbers[1:]:\n",
+    "        distance = abs(x - number)\n",
+    "        if distance < min_distance:\n",
+    "            closest_number = number\n",
+    "            min_distance = distance\n",
+    "    return closest_number\n",
+    "\n",
+    "def search(df, query):\n",
+    "    product = model.encode(query).tolist()\n",
+    "    # product = df.iloc[0]['text_vector_'] #use one of the products as sample\n",
+    "\n",
+    "    nbrs = NearestNeighbors(n_neighbors=3, algorithm='ball_tree').fit(df['text_vector_'].values.tolist())\n",
+    "    distances, indices = nbrs.kneighbors([product]) #input the vector of the reference object\n",
+    "\n",
+    "    #print out the description of every recommended product\n",
+    "    df_search = df.iloc[list(indices)[0]].drop(['text_vector_'], axis=1) #.sort_values('avgFeedbackScore', ascending=False)\n",
+    "\n",
+    "    return df_search.sort_values('price', ascending=False)\n",
+    "\n",
+    "def filter_df(df, column_name, filter_type, filter_value):\n",
+    "    if filter_type == '==':\n",
+    "        df_filtered = df[df[column_name]==filter_value]\n",
+    "    elif filter_type == '>=':\n",
+    "        df_filtered = df[df[column_name]>=filter_value]\n",
+    "    elif filter_type == '<=':\n",
+    "        df_filtered = df[df[column_name]<=filter_value]\n",
+    "    return df_filtered"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def predict(history, input1, input2, input3, input4):\n",
+    "    history.append([input1, input2, input3, input4])\n",
+    "\n",
+    "    print(history)\n",
+    "    df_location = filter_df(df, 'location', '==', input3)\n",
+    "    df_size = filter_df(df_location, 'sq. meters', '==', input2)\n",
+    "    df_price = filter_df(df_size, 'price', '<=', input1)\n",
+    "    df_result = search(df_price, input4)\n",
+    "\n",
+    "    prediction = [\n",
+    "        round(statistics.mean([x[0] for x in history])), #price\n",
+    "        closest_number(statistics.mean([x[1] for x in history])), #square meters\n",
+    "        statistics.mode([x[2] for x in history]) #state\n",
+    "    ]\n",
+    "\n",
+    "    print(history)\n",
+    "\n",
+    "    return df_result, prediction"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\ardit\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\gradio\\deprecation.py:43: UserWarning: You have unused kwarg parameters in Slider, please remove them: {'step_size': 100}\n",
+      "  warnings.warn(\n",
+      "c:\\Users\\ardit\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\gradio\\deprecation.py:43: UserWarning: You have unused kwarg parameters in Radio, please remove them: {'multiselect': False}\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7863\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7863/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[700, 45, 'Brooklyn', 'I want to take a break from work 😴!!!']]\n",
+      "[[700, 45, 'Brooklyn', 'I want to take a break from work 😴!!!']]\n",
+      "[[700, 45, 'Brooklyn', 'I want to take a break from work 😴!!!'], [700, 45, 'Brooklyn', 'I want to take a break from work 😴!!!']]\n",
+      "[[700, 45, 'Brooklyn', 'I want to take a break from work 😴!!!'], [700, 45, 'Brooklyn', 'I want to take a break from work 😴!!!']]\n"
+     ]
+    }
+   ],
+   "source": [
+    "with gr.Blocks(theme=gr.themes.Soft(primary_hue='amber', secondary_hue='gray', neutral_hue='amber')) as demo:\n",
+    "    history = gr.Variable(value=[]) #beginning\n",
+    "    gr.Markdown(\n",
+    "    \"\"\"\n",
+    "    # Airbnb Search Engine\n",
+    "    \"\"\"\n",
+    "    )\n",
+    "    input1 = gr.Slider(100, 1200, value=700, step_size=100, label=\"Max Price\")\n",
+    "    input2 = gr.Radio([25, 40, 45, 55, 60, 70], multiselect=False, label='square meters', value=45)\n",
+    "    input3 = gr.Radio(['Manhattan', 'Brooklyn', 'Queens', 'Bronx'], multiselect=False, label='State', value='Brooklyn')\n",
+    "    input4 = gr.Textbox(label='Query', value='I want to take a break from work 😴!!!')\n",
+    "\n",
+    "    btn = gr.Button(value=\"Search for a Room\")\n",
+    "    output1 = gr.Dataframe()\n",
+    "    output2 = gr.Textbox(label='prediction for the next search')\n",
+    "    # btn.click(greet, inputs='text', outputs=['dataframe'])\n",
+    "    btn.click(predict, [history, input1, input2, input3, input4], [output1, output2])\n",
+    "demo.launch(share=False)"
+   ]
   }
  ],
  "metadata": {

app.py

@@ -23,7 +23,7 @@ model = SentenceTransformer('all-mpnet-base-v2') #all-MiniLM-L6-v2 #all-mpnet-ba
 # nbrs = NearestNeighbors(n_neighbors=3, algorithm='ball_tree').fit(df['text_vector_'].values.tolist())
 
 def closest_number(x):
-    closest_numbers = [10, 20, 30, 40]
+    closest_numbers = [25, 40, 45, 55, 60, 70]
     closest_number = closest_numbers[0]
     min_distance = abs(x - closest_number)
     for number in closest_numbers[1:]:
@@ -54,8 +54,7 @@ def filter_df(df, column_name, filter_type, filter_value):
         df_filtered = df[df[column_name]<=filter_value]
     return df_filtered
 
-history = list()
-def predict(input1, input2, input3, input4):
+def predict(history, input1, input2, input3, input4):
     history.append([input1, input2, input3, input4])
 
     print(history)
@@ -66,13 +65,14 @@ def predict(input1, input2, input3, input4):
 
     prediction = [
         round(statistics.mean([x[0] for x in history])), #price
-        closest_number(statistics.mean([x[1] for x in history])), #square room
+        closest_number(statistics.mean([x[1] for x in history])), #square meters
         statistics.mode([x[2] for x in history]) #state
     ]
 
     return df_result, prediction
 
 with gr.Blocks(theme=gr.themes.Soft(primary_hue='amber', secondary_hue='gray', neutral_hue='amber')) as demo:
+    history = gr.Variable(value=[]) #beginning
     gr.Markdown(
     """
     # Airbnb Search Engine
@@ -80,12 +80,12 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue='amber', secondary_hue='gray', n
     )
     input1 = gr.Slider(100, 1200, value=700, step_size=100, label="Max Price")
     input2 = gr.Radio([25, 40, 45, 55, 60, 70], multiselect=False, label='square meters', value=45)
-    input3 = gr.Radio(['Manhattan', 'Brooklyn', 'Queens', 'Bronx'], multiselect=False, label='State', value='Queens')
+    input3 = gr.Radio(['Manhattan', 'Brooklyn', 'Queens', 'Bronx'], multiselect=False, label='State', value='Brooklyn')
     input4 = gr.Textbox(label='Query', value='I want to take a break from work 😴!!!')
 
     btn = gr.Button(value="Search for a Room")
     output1 = gr.Dataframe()
     output2 = gr.Textbox(label='prediction for the next search')
     # btn.click(greet, inputs='text', outputs=['dataframe'])
-    btn.click(predict, [input1, input2, input3, input4], [output1, output2])
+    btn.click(predict, [history, input1, input2, input3, input4], [output1, output2])
 demo.launch(share=False)

history.ipynb

@@ -0,0 +1,107 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\ardit\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\gradio\\deprecation.py:43: UserWarning: You have unused kwarg parameters in Radio, please remove them: {'multiselect': False}\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running on local URL:  http://127.0.0.1:7861\n",
+      "\n",
+      "To create a public link, set `share=True` in `launch()`.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div><iframe src=\"http://127.0.0.1:7861/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": []
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[40]\n",
+      "[40, 30]\n",
+      "[40, 30, 10]\n",
+      "[40, 30, 10, 10]\n",
+      "[40, 30, 10, 10, 10]\n"
+     ]
+    }
+   ],
+   "source": [
+    "import gradio as gr\n",
+    "import statistics\n",
+    "\n",
+    "def predict(history, input1):\n",
+    "    history.append(input1)\n",
+    "\n",
+    "    print(history)\n",
+    "    total = statistics.mean(history)\n",
+    "\n",
+    "    return total\n",
+    "\n",
+    "with gr.Blocks(theme=gr.themes.Soft(primary_hue='amber', secondary_hue='gray', neutral_hue='amber')) as demo:\n",
+    "    gr.Markdown(\n",
+    "    \"\"\"\n",
+    "    # Gradio with History\n",
+    "    \"\"\"\n",
+    "    )\n",
+    "    history = gr.Variable(value=[]) #beginning\n",
+    "    input1 = gr.Radio([10, 20, 30, 40, 50], multiselect=False, label='value')\n",
+    "    btn = gr.Button(value=\"Search for a Room\")\n",
+    "    output1 = gr.Textbox(label='value')\n",
+    "    # btn.click(greet, inputs='text', outputs=['dataframe'])\n",
+    "    btn.click(predict, [history, input1], [output1])\n",
+    "demo.launch(share=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}