Update app.py

app.py

@@ -3,13 +3,33 @@ import pandas as pd
 import plotly.graph_objects as go
 from datasets import load_dataset
 
-dataset = load_dataset("gradio/NYC-Airbnb-Open-Data", split="train")
-df = dataset.to_pandas()
+dataset = load_dataset('text', data_files={'train': ['NPI_2023_01_17-05.10.57.PM.csv'], 'test': 'NPI_2023_01_17-05.10.57.PM.csv'})
+
+#1.6GB NPI file with MH therapy taxonomy provider codes (NUCC based) with human friendly replacement labels (e.g. Counselor rather than code)
+#datasetNPIMH = load_dataset("awacke1/NPI-Providers-And-Facilities-By-Taxonomy", split="train")
+#datasetNPIMH = load_dataset("awacke1/NPI-Providers-And-Facilities-By-Taxonomy", split='train[:1%]')
+#print(datasetNPIMH.shape)
+
+datasetNYC = load_dataset("gradio/NYC-Airbnb-Open-Data", split="train")
+df = datasetNYC.to_pandas()
+
+def MatchText(pddf, name):
+    pd.set_option("display.max_rows", None)
+    data = pddf
+    swith=data.loc[data['text'].str.contains(name, case=False, na=False)]
+    return swith
+
+def getDatasetFind(findString):
+    #finder = dataset.filter(lambda example: example['text'].find(findString))
+    finder = dataset['train'].filter(lambda example: example['text'].find(findString))
+    finder = finder = finder.to_pandas()
+    g1=MatchText(finder, findString)
+    
+    return g1
 
 def filter_map(min_price, max_price, boroughs):
 
-    filtered_df = df[(df['neighbourhood_group'].isin(boroughs)) & 
-          (df['price'] > min_price) & (df['price'] < max_price)]
+    filtered_df = df[(df['neighbourhood_group'].isin(boroughs)) & (df['price'] > min_price) & (df['price'] < max_price)]
     names = filtered_df["name"].tolist()
     prices = filtered_df["price"].tolist()
     text_list = [(names[i], prices[i]) for i in range(0, len(names))]
@@ -49,7 +69,17 @@ with gr.Blocks() as demo:
         boroughs = gr.CheckboxGroup(choices=["Queens", "Brooklyn", "Manhattan", "Bronx", "Staten Island"], value=["Queens", "Brooklyn"], label="Select Boroughs:")
         btn = gr.Button(value="Update Filter")
         map = gr.Plot().style()
+        
+        with gr.Row():
+            df20 = gr.Textbox(lines=4, default="", label="Find Text:")
+            btn2 = gr.Button(value="Find")
+            #df21 = gr.Textbox(lines=4, default="", label="Found:")
+        with gr.Row():
+            df4 = gr.Dataframe(wrap=True, max_rows=10000, overflow_row_behaviour= "paginate")
+
     demo.load(filter_map, [min_price, max_price, boroughs], map)
     btn.click(filter_map, [min_price, max_price, boroughs], map)
+    
+    btn2.click(getDatasetFind,df20,df4 )
 
 demo.launch()