Update app.py

app.py

@@ -129,7 +129,7 @@ def predict_single_text(text):
     predicted_prob = [round(a_, 3) for a_ in probabilities.cpu().numpy().tolist() if a_ > threshold]
 
     # Create a dictionary containing the top predicted IEQ labels and their corresponding probabilities
-    top_prediction = (dict(zip(predicted_labels, predicted_prob)))
+    top_prediction = predicted_labels
 
     # Create a bar chart showing the likelihood of each IEQ label
     # Make dataframe for plotly bar chart
@@ -141,7 +141,7 @@ def predict_single_text(text):
     df2['Likelihood'] = n
 
     # plot graph of predictions
-    fig = px.bar(df2, x="Likelihood", y="IEQ", orientation="h")
+    fig = px.bar(df2, x="Likelihood", y="IEQ", orientation="v")
 
     fig.update_layout(
         # barmode='stack',
@@ -160,9 +160,7 @@ def predict_single_text(text):
 
     return top_prediction, fig
 
-    # Create Gradio interface for single text
-
-
+# Create Gradio interface for single text
 iface2 = gr.Interface(fn=predict_single_text,
                       inputs=gr.Textbox(lines=7, label="Paste or type text here"),
                       outputs=[gr.Label(label="Top Prediction", show_label=True),
@@ -333,22 +331,22 @@ def predict_from_csv(file, column_name, progress=gr.Progress()):
     # Create a downloadable CSV file
     output_csv = gr.File(value='IEQ_predictions.csv', visible=True)
 
-    # Create a histogram showing the frequency of each IEQ label
-    fig = px.histogram(df_docs, y="IEQ_predicted")
-    fig.update_layout(
-        template='seaborn',
-        font=dict(family="Arial", size=12, color="black"),
-        autosize=True,
-        # width=800,
-        # height=500,
-        xaxis_title="IEQ counts",
-        yaxis_title="Indoor environmental quality (IEQ)",
-    )
-    fig.update_xaxes(tickangle=0, tickfont=dict(family='Arial', color='black', size=12))
-    fig.update_yaxes(tickangle=0, tickfont=dict(family='Arial', color='black', size=12))
-    fig.update_annotations(font_size=12)
+    # # Create a histogram showing the frequency of each IEQ label
+    # fig = px.histogram(df_docs, y="IEQ_predicted")
+    # fig.update_layout(
+    #     template='seaborn',
+    #     font=dict(family="Arial", size=12, color="black"),
+    #     autosize=True,
+    #     # width=800,
+    #     # height=500,
+    #     xaxis_title="IEQ counts",
+    #     yaxis_title="Indoor environmental quality (IEQ)",
+    # )
+    # fig.update_xaxes(tickangle=0, tickfont=dict(family='Arial', color='black', size=12))
+    # fig.update_yaxes(tickangle=0, tickfont=dict(family='Arial', color='black', size=12))
+    # fig.update_annotations(font_size=12)
 
-    return fig, output_csv
+    return output_csv, #fig
 
 
 # Define the input component
@@ -358,8 +356,7 @@ column_name_input = gr.Textbox(label="Enter the column name containing the text
 # Create the Gradio interface
 iface3 = gr.Interface(fn=predict_from_csv,
                       inputs=[file_input, column_name_input],
-                      outputs=[gr.Plot(label='Frequency of IEQs', show_label=True),
-                               gr.File(label='Download output CSV', show_label=True)],
+                      outputs=[gr.File(label='Download output CSV', show_label=True)],
                       title="Multi-text Prediction",
                       description='**NOTE:** Please enter the column name containing the text to be analyzed.')