Update app.py

app.py

@@ -6,13 +6,13 @@ import altair as alt
 url = 'https://github.com/UIUC-iSchool-DataViz/is445_data/raw/main/licenses_fall2022.csv'
 df = pd.read_csv(url)
 
-# Ensure all object columns are explicitly converted to string for compatibility with Arrow
+# Convert object columns to string for compatibility
 for col in df.select_dtypes(include=['object']).columns:
     df[col] = df[col].astype(str)
 
-# Convert integer columns to float to handle potential NaN values
-for col in df.select_dtypes(include=['int64']).columns:
-    df[col] = df[col].astype(float)
+# Convert integer columns to float
+for col in df.select_dtypes(include=['int64', 'float64']).columns:
+    df[col] = pd.to_numeric(df[col], errors='coerce')
 
 # Checking for missing values and handling them
 df['Middle'] = df['Middle'].fillna('N/A')  # Update Middle column without inplace
@@ -25,19 +25,18 @@ df.dropna(subset=['License Number', 'First Name', 'Last Name', 'Effective Date',
                   'Expiration Date', 'City', 'Zip', 'County', 'Specialty/Qualifier',
                   'Controlled Substance Schedule', 'Action'], inplace=True)
 
-# Ensure datetime columns are correctly formatted
+# Convert datetime columns
 date_columns = ['Original Issue Date', 'Effective Date', 'Expiration Date', 'LastModifiedDate']
 for col in date_columns:
     df[col] = pd.to_datetime(df[col], errors='coerce', format='%m/%d/%Y')
 
-# Adding year columns for analysis
+# Add year columns
 df['Original Issue Year'] = df['Original Issue Date'].dt.year
 df['Effective Date Year'] = df['Effective Date'].dt.year
 df['Expiration Date Year'] = df['Expiration Date'].dt.year
 df['Last Modified Date Year'] = df['LastModifiedDate'].dt.year
 
-# Display dataset preview and column data types
-st.write("Dataset Preview", df.head())
+# Final check of data types
 st.write("Column Data Types:", df.dtypes)
 
 # # Converting object columns to category for better memory management