Feature/chapter 7 forecast

Chapter01/forecasting/forecasting_example.py

@@ -26,12 +26,14 @@ def plot_store_data(df: pd.DataFrame) -> None:
     fig, ax = plt.subplots(figsize=(20,10))
     df.plot(x='ds', y='y', ax=ax)
     ax.set_xlabel('Date')
-    ax.set_ylabel('Volume')
+    ax.set_ylabel('Sales')
     ax.legend(['Truth'])
     current_ytick_values = plt.gca().get_yticks()
     plt.gca().set_yticklabels(['{:,.0f}'.format(x) for x in current_ytick_values])
     plt.savefig('store_data.png')
+
 
+
 def train_predict(
     df: pd.DataFrame, 
     train_fraction: float, 
@@ -74,17 +76,17 @@ def plot_forecast(df_train: pd.DataFrame, df_test: pd.DataFrame, predicted: pd.D
         x='ds', 
         y='yhat', 
         ax=ax, 
-        label='Prediction', 
+        label='Prediction + 95% CI', 
         linewidth=2, 
         markersize=5, 
-        color='k'
+        color='red'
     )
     ax.fill_between(
         x=predicted['ds'], 
         y1=predicted['yhat_upper'], 
         y2=predicted['yhat_lower'], 
-        alpha=0.1, 
-        color='k'
+        alpha=0.15, 
+        color='red',
     )
     df_train.iloc[train_index-100:].plot(
         x='ds', 
@@ -99,6 +101,7 @@ def plot_forecast(df_train: pd.DataFrame, df_test: pd.DataFrame, predicted: pd.D
     plt.gca().set_yticklabels(['{:,.0f}'.format(x) for x in current_ytick_values])
     ax.set_xlabel('Date')
     ax.set_ylabel('Sales')
+    plt.tight_layout()
     plt.savefig('store_data_forecast.png')
 
 
@@ -107,29 +110,35 @@ def plot_forecast(df_train: pd.DataFrame, df_test: pd.DataFrame, predicted: pd.D
 if __name__ == "__main__":
     import os
 
-    # If data present, read it in
+    # If data present, read it in, otherwise, download it 
     file_path = 'rossman_store_data/train.csv'
     if os.path.exists(file_path):
         logging.info('Dataset found, reading into pandas dataframe.')
         df = pd.read_csv(file_path)
     else:
         logging.info('Dataset not found, downloading ...')
-        download_kaggle_dataset()    
-
+        download_kaggle_dataset()
+        logging.info('Reading dataset into pandas dataframe.')
+        df = pd.read_csv(file_path)   
+
+    # Transform dataset in preparation for feeding to Prophet
     df = prep_store_data(df)
 
+    # Define main parameters for modelling
     seasonality = {
         'yearly': True,
         'weekly': True,
         'daily': False
     }
-
+
+    # Calculate the relevant dataframes
     predicted, df_train, df_test, train_index = train_predict(
         df = df,
         train_fraction = 0.8,
         seasonality=seasonality
     )
 
+    # Plot the forecast
     plot_forecast(df_train, df_test, predicted)
 
 

Chapter01/mlewp-chapter01.yml

@@ -20,26 +20,42 @@ dependencies:
   - pip:
       - aiohttp==3.8.4
       - aiosignal==1.3.1
+      - anyio==3.6.2
       - appdirs==1.4.4
+      - appnope==0.1.3
+      - argon2-cffi==21.3.0
+      - argon2-cffi-bindings==21.2.0
+      - arrow==1.2.3
+      - asttokens==2.2.1
       - async-timeout==4.0.2
       - attrs==22.2.0
+      - backcall==0.2.0
+      - beautifulsoup4==4.12.0
+      - bleach==6.0.0
       - build==0.10.0
       - cachecontrol==0.12.11
       - certifi==2022.12.7
       - cffi==1.15.1
       - charset-normalizer==3.1.0
       - cleo==2.0.1
       - cmdstanpy==1.1.0
+      - comm==0.1.3
       - contourpy==1.0.7
       - convertdate==2.4.0
       - crashtest==0.4.1
       - cycler==0.11.0
       - cython==0.29.33
+      - debugpy==1.6.6
+      - decorator==5.1.1
+      - defusedxml==0.7.1
       - distlib==0.3.6
       - dulwich==0.21.3
       - ephem==4.1.4
+      - executing==1.2.0
+      - fastjsonschema==2.16.3
       - filelock==3.10.3
       - fonttools==4.39.2
+      - fqdn==1.5.1
       - frozenlist==1.3.3
       - hijri-converter==2.2.4
       - holidays==0.21.13
@@ -48,54 +64,105 @@ dependencies:
       - idna==3.4
       - importlib-metadata==6.1.0
       - installer==0.7.0
+      - ipykernel==6.22.0
+      - ipython==8.11.0
+      - ipython-genutils==0.2.0
+      - isoduration==20.11.0
       - jaraco-classes==3.2.3
+      - jedi==0.18.2
+      - jinja2==3.1.2
       - joblib==1.2.0
+      - jsonpointer==2.3
       - jsonschema==4.17.3
+      - jupyter-client==8.1.0
+      - jupyter-core==5.3.0
+      - jupyter-events==0.6.3
+      - jupyter-server==2.5.0
+      - jupyter-server-terminals==0.4.4
+      - jupyterlab-pygments==0.2.2
+      - kaggle==1.5.13
       - keyring==23.13.1
       - kiwisolver==1.4.4
       - korean-lunar-calendar==0.3.1
       - lockfile==0.12.2
       - lunarcalendar==0.0.9
+      - markupsafe==2.1.2
       - marshmallow==3.19.0
       - matplotlib==3.7.1
+      - matplotlib-inline==0.1.6
+      - mistune==2.0.5
       - more-itertools==9.1.0
       - msgpack==1.0.5
       - multidict==6.0.4
+      - nbclassic==0.5.3
+      - nbclient==0.7.2
+      - nbconvert==7.2.10
+      - nbformat==5.8.0
+      - nest-asyncio==1.5.6
+      - notebook==6.5.3
+      - notebook-shim==0.2.2
       - numpy==1.24.2
       - packaging==23.0
       - pandas==1.5.3
+      - pandocfilters==1.5.0
+      - parso==0.8.3
       - pexpect==4.8.0
+      - pickleshare==0.7.5
       - pillow==9.4.0
       - pkginfo==1.9.6
       - platformdirs==2.6.2
       - poetry==1.4.1
       - poetry-core==1.5.2
       - poetry-plugin-export==1.3.0
+      - prometheus-client==0.16.0
+      - prompt-toolkit==3.0.38
       - prophet==1.1.2
+      - psutil==5.9.4
       - ptyprocess==0.7.0
+      - pure-eval==0.2.2
       - pycparser==2.21
+      - pygments==2.14.0
       - pymeeus==0.5.12
       - pyparsing==3.0.9
       - pyproject-hooks==1.0.0
       - pyrsistent==0.19.3
       - python-dateutil==2.8.2
+      - python-json-logger==2.0.7
+      - python-slugify==8.0.1
       - pytz==2022.7.1
+      - pyyaml==6.0
+      - pyzmq==25.0.2
       - rapidfuzz==2.13.7
       - requests==2.28.2
       - requests-toolbelt==0.10.1
+      - rfc3339-validator==0.1.4
+      - rfc3986-validator==0.1.1
       - scikit-learn==1.2.2
       - scipy==1.10.1
+      - send2trash==1.8.0
       - shellingham==1.5.0.post1
       - six==1.16.0
+      - sniffio==1.3.0
+      - soupsieve==2.4
+      - stack-data==0.6.2
+      - terminado==0.17.1
+      - text-unidecode==1.3
       - threadpoolctl==3.1.0
+      - tinycss2==1.2.1
       - tomli==2.0.1
       - tomlkit==0.11.6
+      - tornado==6.2
       - tqdm==4.65.0
+      - traitlets==5.9.0
       - trove-classifiers==2023.3.9
+      - uri-template==1.2.0
       - urllib3==1.26.15
       - virtualenv==20.21.0
+      - wcwidth==0.2.6
       - webargs==8.2.0
+      - webcolors==1.12
       - webencodings==0.5.1
+      - websocket-client==1.5.1
       - xattr==0.10.1
       - yarl==1.8.2
       - zipp==3.15.0

Chapter07/forecast/create-kind-cluster.sh

@@ -0,0 +1 @@
+kind create cluster --name mlewp-chapter07 --config kind-test2-config.yaml

Chapter07/forecast/kind-test2-config.yaml

@@ -0,0 +1,7 @@
+# three node (two workers) cluster config
+kind: Cluster
+apiVersion: kind.x-k8s.io/v1alpha4
+nodes:
+- role: control-plane
+- role: worker
+- role: worker

Chapter07/forecast/kserve-basic/kserve_python_sdk_basic.py

@@ -0,0 +1,58 @@
+'''
+Based on https://www.kubeflow.org/docs/external-add-ons/kserve/first_isvc_kserve/
+
+'''
+from kubernetes import client 
+from kserve import KServeClient
+from kserve import constants
+from kserve import utils
+from kserve import V1beta1InferenceService
+from kserve import V1beta1InferenceServiceSpec
+from kserve import V1beta1PredictorSpec
+from kserve import V1beta1SKLearnSpec
+
+
+# MLFLOW
+
+
+# KUBEFLOW
+namespace = utils.get_default_target_namespace()
+
+name='sklearn-iris'
+kserve_version='v1beta1'
+api_version = constants.KSERVE_GROUP + '/' + kserve_version
+
+isvc = V1beta1InferenceService(api_version=api_version,
+                               kind=constants.KSERVE_KIND,
+                               metadata=client.V1ObjectMeta(
+                                   name=name, namespace=namespace, annotations={'sidecar.istio.io/inject':'false'}),
+                               spec=V1beta1InferenceServiceSpec(
+                               predictor=V1beta1PredictorSpec(
+                               sklearn=(V1beta1SKLearnSpec(
+                                   storage_uri="gs://kfserving-samples/models/sklearn/iris"))))
+)
+
+KServe = KServeClient()
+KServe.create(isvc)
+
+KServe.get(name, namespace=namespace, watch=True, timeout_seconds=120)
+
+'''
+
+'''
+import requests
+
+isvc_resp = KServe.get(name, namespace=namespace)
+isvc_url = isvc_resp['status']['address']['url']
+
+print(isvc_url)
+
+inference_input = {
+  'instances': [
+    [6.8,  2.8,  4.8,  1.4],
+    [6.0,  3.4,  4.5,  1.6]
+  ]
+}
+
+response = requests.post(isvc_url, json=inference_input)
+print(response.text)