changes

app.py

@@ -2,44 +2,49 @@ import gradio as gr
 import numpy as np
 from PIL import Image
 import requests
-
+from feature_engineering import feat_eng
 import hopsworks
 import joblib
+import pandas as pd
 
 project = hopsworks.login()
 fs = project.get_feature_store()
 
 
 mr = project.get_model_registry()
-model = mr.get_model("iris_modal", version=1)
+model = mr.get_model("titanic_modal_simple_classifier", version=1)
 model_dir = model.download()
-model = joblib.load(model_dir + "/iris_model.pkl")
-
+model = joblib.load(model_dir + "/titanic_model.pkl")
+leo_url = "https://media.tenor.com/FghTtX3ZgbAAAAAC/drowning-leo.gif"
+rose_url = "https://media4.giphy.com/media/6A5zBPtbknIGY/giphy.gif?cid=ecf05e477syp5zeoheii45de76uicvgu0nuegojslz3zgodt&rid=giphy.gif&ct=g"
 
-def iris(sepal_length, sepal_width, petal_length, petal_width):
-    input_list = []
-    input_list.append(sepal_length)
-    input_list.append(sepal_width)
-    input_list.append(petal_length)
-    input_list.append(petal_width)
+def titanic(pclass, name, sex, age, sibsp, parch, ticket, fare, cabin, embarked):
+    df_pre = pd.DataFrame({"PassengerId":[-1], "Pclass": [pclass], "Name": [name], "Sex": [sex], "Age": [age], "SibSp": [sibsp], "Parch": [parch], "Ticket": [ticket], "Fare": [fare], "Cabin": [cabin], "Embarked": [embarked]})
+    df_post = feat_eng(df_pre)
     # 'res' is a list of predictions returned as the label.
-    res = model.predict(np.asarray(input_list).reshape(1, -1)) 
+    res = model.predict(df_post)[0]
     # We add '[0]' to the result of the transformed 'res', because 'res' is a list, and we only want 
     # the first element.
-    flower_url = "https://raw.githubusercontent.com/featurestoreorg/serverless-ml-course/main/src/01-module/assets/" + res[0] + ".png"
-    img = Image.open(requests.get(flower_url, stream=True).raw)            
+    
+    img = Image.open(leo_url) if res == 0 else Image.open(rose_url)
     return img
         
-demo = gr.Interface(
-    fn=iris,
-    title="Iris Flower Predictive Analytics",
-    description="Experiment with sepal/petal lengths/widths to predict which flower it is.",
+demo = gr.Interface(    
+    fn=titanic,
+    title="Titanic Survival Predictive Analytics",
+    description="Experiment with Titanic Passenger data to predict survival",
     allow_flagging="never",
     inputs=[
-        gr.inputs.Number(default=1.0, label="sepal length (cm)"),
-        gr.inputs.Number(default=1.0, label="sepal width (cm)"),
-        gr.inputs.Number(default=1.0, label="petal length (cm)"),
-        gr.inputs.Number(default=1.0, label="petal width (cm)"),
+        gr.inputs.Number(default=1.0, label="pclass, [1,2,3]"),
+        gr.inputs.Textbox(default="Anton", label="name"),
+        gr.inputs.Textbox(default="male", label="sex, male or female"),
+        gr.inputs.Number(default=25, label="age"),
+        gr.inputs.Number(default=2, label="sibsb"),
+        gr.inputs.Number(default=2, label="parch"),
+        gr.inputs.Textbox(default="blabla", label="Ticket"),
+        gr.inputs.Number(default=200, label="Fare"),
+        gr.inputs.Textbox(default="blabla", label="Cabin"),
+        gr.inputs.Textbox(default="blabla", label="Embarked: [S, C, Q]")
         ],
     outputs=gr.Image(type="pil"))
 

requirements.txt

@@ -5,4 +5,5 @@ seaborn
 pandas
 numpy
 dataframe-image
-modal-client
+modal-client
+gradio