Update app.py

app.py

@@ -1087,6 +1087,45 @@ if analysis_option == 'Machine Learning':
 
 
 
+def word_cloud(data):
+    no_nan = data.dropna(subset=['ImmunizationName'])
+    immu = list(no_nan['ImmunizationName'])
+    filtered_data = [item for item in immu if item and not pd.isna(item)]
+    unique_values = set(filtered_data)
+    my_string = ' '.join(unique_values)
+    lmao = my_string.strip(', ')
+    lmao = lmao.replace(',', '')
+    
+    cloud = WordCloud(
+        scale=3,
+        max_words=150,
+        colormap='RdYlGn',
+        mask=None,
+        background_color='white',
+        stopwords=None,
+        collocations=True,
+        contour_color='black',
+        contour_width=1
+    ).generate(lmao)
+    
+    # Create a Matplotlib figure
+    fig, ax = plt.subplots(figsize=(10, 6))
+    ax.imshow(cloud, interpolation='bilinear')
+    ax.axis('off')  # Remove the axes
+    ax.set_title('Immunization Word Cloud', color='black', fontsize=20)
+    
+    # Return the figure to be used in Streamlit
+    return fig
+
+def more_scatter(data):
+    component_icd_counts = data.groupby(['ComponentName', 'GroupedICD','Description']).size().reset_index(name='Count')
+    component_icd_counts = component_icd_counts[component_icd_counts['Count']> 900]
+    import plotly.express as px
+    # Scatter plot
+    fig16 = px.scatter(component_icd_counts, y='ComponentName', x='Description', size='Count',
+                    hover_name='ComponentName', color='Count', title='Lab Component-ICD Relationship',color_continuous_scale='YlOrBr')
+    fig16.update_layout(template="plotly_dark",xaxis_title='ICD Code', yaxis_title='Component Name', coloraxis_colorbar=dict(title='Count'))
+    return fig16
 
 
 
@@ -1140,6 +1179,9 @@ if analysis_option == 'Data':
     col6 = st.columns(1)[0]
     fig_man = scatter_man(data)
     col6.plotly_chart(fig_man, use_container_width=True)
+    fig16 = more_scatter(data)
+    col8 = st.columns(1)[0]
+    col8.plotly_chart(fig16, use_container_width=True)
 
     st.dataframe(data.head(20).style.format({'PatientID': "{:.0f}"}))
 
@@ -1197,6 +1239,9 @@ if analysis_option == 'EDA':
         col12, col13 = st.columns(2)
         fig10 = chart_11(health_data)
         col12.plotly_chart(fig10, use_container_width=True)
+
+        fig11 = word_cloud(health_data)
+        col13.pyplot(fig11, use_container_width=True)
         
         st.dataframe(health_data.head(20).style.format({'PatientID': "{:.0f}"}))