changes

_test.ipynb

@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 47,
    "metadata": {},
    "outputs": [
     {
@@ -66,7 +66,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Running on local URL:  http://127.0.0.1:7884\n",
+      "Running on local URL:  http://127.0.0.1:7887\n",
       "\n",
       "To create a public link, set `share=True` in `launch()`.\n"
      ]
@@ -74,7 +74,7 @@
     {
      "data": {
       "text/html": [
-       "<div><iframe src=\"http://127.0.0.1:7884/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
+       "<div><iframe src=\"http://127.0.0.1:7887/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -87,238 +87,9 @@
      "data": {
       "text/plain": []
      },
-     "execution_count": 44,
+     "execution_count": 47,
      "metadata": {},
      "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>name</th>\n",
-       "      <th>raised</th>\n",
-       "      <th>target</th>\n",
-       "      <th>size</th>\n",
-       "      <th>stage</th>\n",
-       "      <th>country</th>\n",
-       "      <th>source</th>\n",
-       "      <th>description</th>\n",
-       "      <th>tags</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>78931</th>\n",
-       "      <td>Developeration</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>11-500+</td>\n",
-       "      <td>c</td>\n",
-       "      <td>sweden</td>\n",
-       "      <td>https://www.startupblink.com</td>\n",
-       "      <td>Developeration AB was founded 2016 and is a st...</td>\n",
-       "      <td>['healthtech']</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>77566</th>\n",
-       "      <td>ComplyAdvantage</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>11-500+</td>\n",
-       "      <td>c</td>\n",
-       "      <td>united-kingdom</td>\n",
-       "      <td>https://www.startupblink.com</td>\n",
-       "      <td>We are a financial crime solutions provider co...</td>\n",
-       "      <td>['fintech']</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>78674</th>\n",
-       "      <td>Atlas</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>11-500+</td>\n",
-       "      <td>c</td>\n",
-       "      <td>russia</td>\n",
-       "      <td>https://www.startupblink.com</td>\n",
-       "      <td>Atlas Biomedical Holding is developing a netwo...</td>\n",
-       "      <td>['healthtech']</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>81682</th>\n",
-       "      <td>48 Factoring Inc</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>11-500+</td>\n",
-       "      <td>c</td>\n",
-       "      <td>united-states</td>\n",
-       "      <td>https://www.startupblink.com</td>\n",
-       "      <td>48 Factoring Inc. is a financial services comp...</td>\n",
-       "      <td>['fintech']</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>78926</th>\n",
-       "      <td>Xinca</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>11-500+</td>\n",
-       "      <td>c</td>\n",
-       "      <td>argentina</td>\n",
-       "      <td>https://www.startupblink.com</td>\n",
-       "      <td>Incorporar residuos en la fabricaci&amp;oacute;n d...</td>\n",
-       "      <td>['energy' 'environment']</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>80432</th>\n",
-       "      <td>Glow</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>11-500+</td>\n",
-       "      <td>c</td>\n",
-       "      <td>china</td>\n",
-       "      <td>https://www.startupblink.com</td>\n",
-       "      <td>Glow is an ambitious enterprise that uniquely ...</td>\n",
-       "      <td>['healthtech']</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>77716</th>\n",
-       "      <td>Owiwi</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>11-500+</td>\n",
-       "      <td>c</td>\n",
-       "      <td>greece</td>\n",
-       "      <td>https://www.startupblink.com</td>\n",
-       "      <td>Owiwi is a fun and engaging psychometric tool ...</td>\n",
-       "      <td>['software' 'data']</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>78561</th>\n",
-       "      <td>Quantib</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>11-500+</td>\n",
-       "      <td>c</td>\n",
-       "      <td>the-netherlands</td>\n",
-       "      <td>https://www.startupblink.com</td>\n",
-       "      <td>MRI scan technology to better diagnose -- and ...</td>\n",
-       "      <td>['healthtech']</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>77554</th>\n",
-       "      <td>Earnin</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>11-500+</td>\n",
-       "      <td>c</td>\n",
-       "      <td>united-states</td>\n",
-       "      <td>https://www.startupblink.com</td>\n",
-       "      <td>We're building a platform of community-support...</td>\n",
-       "      <td>['fintech']</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>80694</th>\n",
-       "      <td>Vibrent Health</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>Undisclosed</td>\n",
-       "      <td>11-500+</td>\n",
-       "      <td>c</td>\n",
-       "      <td>united-states</td>\n",
-       "      <td>https://www.startupblink.com</td>\n",
-       "      <td>The future of developing new cures for patient...</td>\n",
-       "      <td>['healthtech']</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>94 rows × 9 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                   name       raised       target     size stage  \\\n",
-       "78931    Developeration  Undisclosed  Undisclosed  11-500+     c   \n",
-       "77566   ComplyAdvantage  Undisclosed  Undisclosed  11-500+     c   \n",
-       "78674             Atlas  Undisclosed  Undisclosed  11-500+     c   \n",
-       "81682  48 Factoring Inc  Undisclosed  Undisclosed  11-500+     c   \n",
-       "78926             Xinca  Undisclosed  Undisclosed  11-500+     c   \n",
-       "...                 ...          ...          ...      ...   ...   \n",
-       "80432              Glow  Undisclosed  Undisclosed  11-500+     c   \n",
-       "77716             Owiwi  Undisclosed  Undisclosed  11-500+     c   \n",
-       "78561           Quantib  Undisclosed  Undisclosed  11-500+     c   \n",
-       "77554            Earnin  Undisclosed  Undisclosed  11-500+     c   \n",
-       "80694    Vibrent Health  Undisclosed  Undisclosed  11-500+     c   \n",
-       "\n",
-       "               country                        source  \\\n",
-       "78931           sweden  https://www.startupblink.com   \n",
-       "77566   united-kingdom  https://www.startupblink.com   \n",
-       "78674           russia  https://www.startupblink.com   \n",
-       "81682    united-states  https://www.startupblink.com   \n",
-       "78926        argentina  https://www.startupblink.com   \n",
-       "...                ...                           ...   \n",
-       "80432            china  https://www.startupblink.com   \n",
-       "77716           greece  https://www.startupblink.com   \n",
-       "78561  the-netherlands  https://www.startupblink.com   \n",
-       "77554    united-states  https://www.startupblink.com   \n",
-       "80694    united-states  https://www.startupblink.com   \n",
-       "\n",
-       "                                             description  \\\n",
-       "78931  Developeration AB was founded 2016 and is a st...   \n",
-       "77566  We are a financial crime solutions provider co...   \n",
-       "78674  Atlas Biomedical Holding is developing a netwo...   \n",
-       "81682  48 Factoring Inc. is a financial services comp...   \n",
-       "78926  Incorporar residuos en la fabricaci&oacute;n d...   \n",
-       "...                                                  ...   \n",
-       "80432  Glow is an ambitious enterprise that uniquely ...   \n",
-       "77716  Owiwi is a fun and engaging psychometric tool ...   \n",
-       "78561  MRI scan technology to better diagnose -- and ...   \n",
-       "77554  We're building a platform of community-support...   \n",
-       "80694  The future of developing new cures for patient...   \n",
-       "\n",
-       "                           tags  \n",
-       "78931            ['healthtech']  \n",
-       "77566               ['fintech']  \n",
-       "78674            ['healthtech']  \n",
-       "81682               ['fintech']  \n",
-       "78926  ['energy' 'environment']  \n",
-       "...                         ...  \n",
-       "80432            ['healthtech']  \n",
-       "77716       ['software' 'data']  \n",
-       "78561            ['healthtech']  \n",
-       "77554               ['fintech']  \n",
-       "80694            ['healthtech']  \n",
-       "\n",
-       "[94 rows x 9 columns]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
     }
    ],
    "source": [
@@ -345,18 +116,22 @@
     "        else:\n",
     "            return x\n",
     "    df_knn = search(df, query)\n",
-    "    #we live the sorting for last\n",
-    "    df_knn = df_knn.sort_values('raised', ascending=False)\n",
     "    df_knn['raised'] = df_knn['raised'].apply(lambda x : raised_zero(x))\n",
     "\n",
     "    df_size = filter_df(df_knn, 'size', '==', size, 1000)\n",
     "    df_target = filter_df(df_size, 'target', 'contains', target, 20)\n",
-    "    df_stage = filter_df(df_target, 'stage', '==', stage.lower(), 10)\n",
+    "\n",
+    "    if stage != 'ALL':\n",
+    "        df_stage = filter_df(df_target, 'stage', '==', stage.lower(), 10)\n",
+    "    else:\n",
+    "        #we bypass the filter\n",
+    "        df_stage = df_target\n",
     "    \n",
-    "    display(df_stage)\n",
+    "    # display(df_stage)\n",
     "    # df_raised = df_target[(df_target['raised'] >= raised) | (df_target['raised'] == 0)]\n",
     "\n",
-    "    return df_stage[0:100]\n",
+    "    #we live the sorting for last\n",
+    "    return df_stage[0:100].sort_values('raised', ascending=False)\n",
     "\n",
     "with gr.Blocks(theme=gr.themes.Soft(primary_hue='amber', secondary_hue='gray', neutral_hue='amber')) as demo:\n",
     "    gr.Markdown(\n",
@@ -366,7 +141,7 @@
     "    )\n",
     "    size = gr.Radio(['1-10', '11-50', '51-200', '201-500', '500+', '11-500+'], multiselect=False, value='11-500+', label='size')\n",
     "    target = gr.Radio(['B2B', 'B2C', 'B2G', 'B2B2C'], multiselect=False, value='B2B', label='target')\n",
-    "    stage = gr.Radio(['pre-seed', 'A', 'B', 'C', 'exit'], multiselect=False, value='C', label='stage')\n",
+    "    stage = gr.Radio(['pre-seed', 'A', 'B', 'C', 'exit', 'ALL'], multiselect=False, value='ALL', label='stage')\n",
     "    # raised = gr.Slider(0, 20, value=5, step_size=1, label=\"Minimum raising (in Millions)\")\n",
     "    query = gr.Textbox(label='Describe the Startup you are searching for', value='age reversing')\n",
     "    btn = gr.Button(value=\"Search for a Startup\")\n",

app.py

@@ -67,7 +67,12 @@ def greet(size, target, stage, query):
 
     df_size = filter_df(df_knn, 'size', '==', size, 1000)
     df_target = filter_df(df_size, 'target', 'contains', target, 20)
-    df_stage = filter_df(df_target, 'stage', '==', stage.lower(), 10)
+
+    if stage != 'ALL':
+        df_stage = filter_df(df_target, 'stage', '==', stage.lower(), 10)
+    else:
+        #we bypass the filter
+        df_stage = df_target
     
     # display(df_stage)
     # df_raised = df_target[(df_target['raised'] >= raised) | (df_target['raised'] == 0)]
@@ -83,7 +88,7 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue='amber', secondary_hue='gray', n
     )
     size = gr.Radio(['1-10', '11-50', '51-200', '201-500', '500+', '11-500+'], multiselect=False, value='11-500+', label='size')
     target = gr.Radio(['B2B', 'B2C', 'B2G', 'B2B2C'], multiselect=False, value='B2B', label='target')
-    stage = gr.Radio(['pre-seed', 'A', 'B', 'C', 'exit'], multiselect=False, value='C', label='stage')
+    stage = gr.Radio(['pre-seed', 'A', 'B', 'C', 'exit', 'ALL'], multiselect=False, value='ALL', label='stage')
     # raised = gr.Slider(0, 20, value=5, step_size=1, label="Minimum raising (in Millions)")
     query = gr.Textbox(label='Describe the Startup you are searching for', value='age reversing')
     btn = gr.Button(value="Search for a Startup")