added final app setup

app.py

@@ -1,13 +1,14 @@
 import gradio as gr
-from .constants import CSV_HEADER, NUMERIC_FEATURE_NAMES, CATEGORICAL_FEATURES_WITH_VOCABULARY, NUMBER_INPUT_COLS
-from .preprocess import create_max_values_map, create_dropdown_default_values_map, create_sample_test_data
-from .predict import batch_predict, user_input_predict
+from utils.constants import CSV_HEADER, NUMERIC_FEATURE_NAMES, NUMBER_INPUT_COLS
+from utils.preprocess import create_max_values_map, create_dropdown_default_values_map, create_sample_test_data, CATEGORICAL_FEATURES_WITH_VOCABULARY
+from utils.predict import batch_predict, user_input_predict
 
 inputs_list = []
 max_values_map = create_max_values_map()
 dropdown_default_values_map = create_dropdown_default_values_map()
 sample_input_df_val = create_sample_test_data()
 
+
 demo = gr.Blocks()
 
 with demo:
@@ -20,7 +21,7 @@ with demo:
         
         with gr.TabItem("Predict using batch of inputs"):
             gr.Markdown("**Input DataFrame** \n")
-            input_df = gr.Dataframe(headers=CSV_HEADER,value=samp,)
+            input_df = gr.Dataframe(headers=CSV_HEADER,value=sample_input_df_val,)
             gr.Markdown("**Output DataFrame** \n")
             output_df = gr.Dataframe()
             gr.Markdown("**Make Predictions**")
@@ -39,7 +40,7 @@ with demo:
                             else:
                                 curr_max_val = max_values_map["max_"+num_variable]
                                 numeric_input = gr.Slider(0,curr_max_val, label=num_variable,step=1)
-                                inputs_list.append(numeric_input)
+                            inputs_list.append(numeric_input)
                 
                 with gr.TabItem("Categorical Inputs"):
                     gr.Markdown("Choose values for categorical inputs here.")

constants.py → utils/constants.py

@@ -1,6 +1,3 @@
-import pandas as pd
-from .preprocess import load_test_data
-
 # Column names.
 CSV_HEADER = [
     "age",
@@ -67,22 +64,4 @@ NUMERIC_FEATURE_NAMES = [
 ##Cols which will use "Number" component of gradio for taking user input
 NUMBER_INPUT_COLS = ['age', 'num_persons_worked_for_employer','weeks_worked_in_year']
 
-test_data = load_test_data()
 
-CATEGORICAL_FEATURES_WITH_VOCABULARY = {
-    feature_name: sorted([str(value) for value in list(test_data[feature_name].unique())])
-    for feature_name in CSV_HEADER
-    if feature_name
-    not in list(NUMERIC_FEATURE_NAMES + [WEIGHT_COLUMN_NAME, TARGET_FEATURE_NAME])
-}
-# All features names.
-FEATURE_NAMES = NUMERIC_FEATURE_NAMES + list(
-    CATEGORICAL_FEATURES_WITH_VOCABULARY.keys()
-)
-# Feature default values.
-COLUMN_DEFAULTS = [
-    [0.0]
-    if feature_name in NUMERIC_FEATURE_NAMES + [TARGET_FEATURE_NAME, WEIGHT_COLUMN_NAME]
-    else ["NA"]
-    for feature_name in CSV_HEADER
-]

predict.py → utils/predict.py

@@ -12,7 +12,7 @@ def batch_predict(input_data):
         1. prediction probability for each class
         2. actual expected outcome for each entry in the input dataframe
     """
-    input_data_file = "prod_data.csv"
+    input_data_file = "input_data.csv"
     labels = ['Probability of Income greater than 50000',"Probability of Income less than 50000","Actual Income"]
     
     predictions_df = pd.DataFrame(columns=labels)

preprocess.py → utils/preprocess.py

@@ -1,10 +1,37 @@
 import tensorflow as tf
 import pandas as pd
-from .constants import CSV_HEADER, TARGET_FEATURE_NAME, WEIGHT_COLUMN_NAME, NUMERIC_FEATURE_NAMES, COLUMN_DEFAULTS, CATEGORICAL_FEATURES_WITH_VOCABULARY
+from .constants import CSV_HEADER, TARGET_FEATURE_NAME, WEIGHT_COLUMN_NAME, NUMERIC_FEATURE_NAMES
 
 
 ##Helper functions for preprocessing of data:
 
+def load_test_data():
+    
+    test_data_url = "https://archive.ics.uci.edu/ml/machine-learning-databases/census-income-mld/census-income.test.gz"
+    test_data = pd.read_csv(test_data_url, header=None, names=CSV_HEADER)
+    
+    return test_data
+
+test_data = load_test_data()
+
+CATEGORICAL_FEATURES_WITH_VOCABULARY = {
+    feature_name: sorted([str(value) for value in list(test_data[feature_name].unique())])
+    for feature_name in CSV_HEADER
+    if feature_name
+    not in list(NUMERIC_FEATURE_NAMES + [WEIGHT_COLUMN_NAME, TARGET_FEATURE_NAME])
+}
+# All features names.
+FEATURE_NAMES = NUMERIC_FEATURE_NAMES + list(
+    CATEGORICAL_FEATURES_WITH_VOCABULARY.keys()
+)
+# Feature default values.
+COLUMN_DEFAULTS = [
+    [0.0]
+    if feature_name in NUMERIC_FEATURE_NAMES + [TARGET_FEATURE_NAME, WEIGHT_COLUMN_NAME]
+    else ["NA"]
+    for feature_name in CSV_HEADER
+]
+
 def process(features, target):
     for feature_name in features:
         if feature_name in CATEGORICAL_FEATURES_WITH_VOCABULARY:
@@ -44,22 +71,14 @@ def create_dropdown_default_values_map():
         dropdown_default_values_map["max_"+col] = max_val
     return dropdown_default_values_map
 
-def load_test_data():
-    
-    test_data_url = "https://archive.ics.uci.edu/ml/machine-learning-databases/census-income-mld/census-income.test.gz"
-    test_data = pd.read_csv(test_data_url, header=None, names=CSV_HEADER)
-    
-    return test_data
-
 def create_sample_test_data():
     
-    test_data = load_test_data()
-    
     test_data["income_level"] = test_data["income_level"].apply(
     lambda x: 0 if x == " - 50000." else 1)
     
     sample_df = test_data.loc[:20,:]
-    sample_df_values = samp.values.tolist()
+    sample_df_values = sample_df.values.tolist()
     
     return sample_df_values
-    
+
+