add wine

src/wine/requirements.txt

@@ -0,0 +1,9 @@
+#If you have windows, install twofish
+#twofish
+hopsworks
+joblib
+scikit-learn==1.1.1
+seaborn
+dataframe-image
+modal
+gradio==3.14

src/wine/wine+quality/winequality.names

@@ -0,0 +1,72 @@
+Citation Request:
+  This dataset is public available for research. The details are described in [Cortez et al., 2009]. 
+  Please include this citation if you plan to use this database:
+
+  P. Cortez, A. Cerdeira, F. Almeida, T. Matos and J. Reis. 
+  Modeling wine preferences by data mining from physicochemical properties.
+  In Decision Support Systems, Elsevier, 47(4):547-553. ISSN: 0167-9236.
+
+  Available at: [@Elsevier] http://dx.doi.org/10.1016/j.dss.2009.05.016
+                [Pre-press (pdf)] http://www3.dsi.uminho.pt/pcortez/winequality09.pdf
+                [bib] http://www3.dsi.uminho.pt/pcortez/dss09.bib
+
+1. Title: Wine Quality 
+
+2. Sources
+   Created by: Paulo Cortez (Univ. Minho), Antonio Cerdeira, Fernando Almeida, Telmo Matos and Jose Reis (CVRVV) @ 2009
+
+3. Past Usage:
+
+  P. Cortez, A. Cerdeira, F. Almeida, T. Matos and J. Reis. 
+  Modeling wine preferences by data mining from physicochemical properties.
+  In Decision Support Systems, Elsevier, 47(4):547-553. ISSN: 0167-9236.
+
+  In the above reference, two datasets were created, using red and white wine samples.
+  The inputs include objective tests (e.g. PH values) and the output is based on sensory data
+  (median of at least 3 evaluations made by wine experts). Each expert graded the wine quality 
+  between 0 (very bad) and 10 (very excellent). Several data mining methods were applied to model
+  these datasets under a regression approach. The support vector machine model achieved the
+  best results. Several metrics were computed: MAD, confusion matrix for a fixed error tolerance (T),
+  etc. Also, we plot the relative importances of the input variables (as measured by a sensitivity
+  analysis procedure).
+
+4. Relevant Information:
+
+   The two datasets are related to red and white variants of the Portuguese "Vinho Verde" wine.
+   For more details, consult: http://www.vinhoverde.pt/en/ or the reference [Cortez et al., 2009].
+   Due to privacy and logistic issues, only physicochemical (inputs) and sensory (the output) variables 
+   are available (e.g. there is no data about grape types, wine brand, wine selling price, etc.).
+
+   These datasets can be viewed as classification or regression tasks.
+   The classes are ordered and not balanced (e.g. there are munch more normal wines than
+   excellent or poor ones). Outlier detection algorithms could be used to detect the few excellent
+   or poor wines. Also, we are not sure if all input variables are relevant. So
+   it could be interesting to test feature selection methods. 
+
+5. Number of Instances: red wine - 1599; white wine - 4898. 
+
+6. Number of Attributes: 11 + output attribute
+
+   Note: several of the attributes may be correlated, thus it makes sense to apply some sort of
+   feature selection.
+
+7. Attribute information:
+
+   For more information, read [Cortez et al., 2009].
+
+   Input variables (based on physicochemical tests):
+   1 - fixed acidity
+   2 - volatile acidity
+   3 - citric acid
+   4 - residual sugar
+   5 - chlorides
+   6 - free sulfur dioxide
+   7 - total sulfur dioxide
+   8 - density
+   9 - pH
+   10 - sulphates
+   11 - alcohol
+   Output variable (based on sensory data): 
+   12 - quality (score between 0 and 10)
+
+8. Missing Attribute Values: None

src/wine/wine-batch-inference-pipeline.py

@@ -0,0 +1,109 @@
+import os
+import modal
+
+LOCAL=True
+
+if LOCAL == False:
+   stub = modal.Stub()
+   hopsworks_image = modal.Image.debian_slim().pip_install(["hopsworks","joblib","seaborn","scikit-learn==1.2.2","dataframe-image"])
+   @stub.function(image=hopsworks_image, schedule=modal.Period(days=1), secret=modal.Secret.from_name("hopsworks api key"))
+   def f():
+       g()
+
+def g():
+    import pandas as pd
+    import hopsworks
+    import joblib
+    import datetime
+    from PIL import Image
+    from datetime import datetime
+    import dataframe_image as dfi
+    from sklearn.metrics import confusion_matrix
+    from matplotlib import pyplot
+    import seaborn as sns
+    import requests
+
+    project = hopsworks.login()
+    fs = project.get_feature_store()
+
+    mr = project.get_model_registry()
+    model = mr.get_model("iris_model", version=2)
+    model_dir = model.download()
+    model = joblib.load(model_dir + "/iris_model.pkl")
+
+    feature_view = fs.get_feature_view(name="iris", version=1)
+    batch_data = feature_view.get_batch_data()
+
+    y_pred = model.predict(batch_data)
+    #print(y_pred)
+    offset = 1
+    flower = y_pred[y_pred.size-offset]
+    flower_url = "https://raw.githubusercontent.com/featurestoreorg/serverless-ml-course/main/src/01-module/assets/" + flower + ".png"
+    print("Flower predicted: " + flower)
+    img = Image.open(requests.get(flower_url, stream=True).raw)            
+    img.save("./latest_iris.png")
+    dataset_api = project.get_dataset_api()    
+    dataset_api.upload("./latest_iris.png", "Resources/images", overwrite=True)
+
+    iris_fg = fs.get_feature_group(name="iris", version=1)
+    df = iris_fg.read() 
+    #print(df)
+    label = df.iloc[-offset]["variety"]
+    label_url = "https://raw.githubusercontent.com/featurestoreorg/serverless-ml-course/main/src/01-module/assets/" + label + ".png"
+    print("Flower actual: " + label)
+    img = Image.open(requests.get(label_url, stream=True).raw)            
+    img.save("./actual_iris.png")
+    dataset_api.upload("./actual_iris.png", "Resources/images", overwrite=True)
+
+    monitor_fg = fs.get_or_create_feature_group(name="iris_predictions",
+                                                version=1,
+                                                primary_key=["datetime"],
+                                                description="Iris flower Prediction/Outcome Monitoring"
+                                                )
+
+    now = datetime.now().strftime("%m/%d/%Y, %H:%M:%S")
+    data = {
+        'prediction': [flower],
+        'label': [label],
+        'datetime': [now],
+       }
+    monitor_df = pd.DataFrame(data)
+    monitor_fg.insert(monitor_df, write_options={"wait_for_job" : False})
+
+    history_df = monitor_fg.read()
+    # Add our prediction to the history, as the history_df won't have it - 
+    # the insertion was done asynchronously, so it will take ~1 min to land on App
+    history_df = pd.concat([history_df, monitor_df])
+
+
+    df_recent = history_df.tail(4)
+    dfi.export(df_recent, './df_recent.png', table_conversion = 'matplotlib')
+    dataset_api.upload("./df_recent.png", "Resources/images", overwrite=True)
+
+    predictions = history_df[['prediction']]
+    labels = history_df[['label']]
+
+    # Only create the confusion matrix when our iris_predictions feature group has examples of all 3 iris flowers
+    print("Number of different flower predictions to date: " + str(predictions.value_counts().count()))
+    if predictions.value_counts().count() == 3:
+        results = confusion_matrix(labels, predictions)
+
+        df_cm = pd.DataFrame(results, ['True Setosa', 'True Versicolor', 'True Virginica'],
+                             ['Pred Setosa', 'Pred Versicolor', 'Pred Virginica'])
+
+        cm = sns.heatmap(df_cm, annot=True)
+        fig = cm.get_figure()
+        fig.savefig("./confusion_matrix.png")
+        dataset_api.upload("./confusion_matrix.png", "Resources/images", overwrite=True)
+    else:
+        print("You need 3 different flower predictions to create the confusion matrix.")
+        print("Run the batch inference pipeline more times until you get 3 different iris flower predictions") 
+
+
+if __name__ == "__main__":
+    if LOCAL == True :
+        g()
+    else:
+        with stub.run():
+            f()
+