get basic onnx export working

.dockerignore

@@ -0,0 +1,18 @@
+exercise_notebooks/*
+*/env*
+*/venv*
+.circleci*
+packages/gradient_boosting_model
+*.env
+*.log
+.git
+.gitignore
+.dockerignore
+*.mypy_cache
+*.pytest_cache
+
+### Python ###
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]

.gitignore

@@ -89,6 +89,7 @@ venv/
 ENV/
 env.bak/
 venv.bak/
+.tox/
 
 # Spyder project settings
 .spyderproject
@@ -102,3 +103,25 @@ venv.bak/
 
 # mypy
 .mypy_cache/
+
+# pycharm
+.idea/
+
+# OSX
+.DS_Store
+
+# all logs
+logs/
+
+# training data
+packages/gradient_boosting_model/gradient_boosting_model/datasets/*.csv
+packages/gradient_boosting_model/gradient_boosting_model/datasets/*.txt
+packages/gradient_boosting_model/gradient_boosting_model/datasets/*.zip
+
+# trained models
+packages/gradient_boosting_model/gradient_boosting_model/trained_models/*.pkl
+*.h5
+
+# differential test artifacts
+packages/ml_api/differential_tests/expected_results/
+packages/ml_api/differential_tests/actual_results/

exercise_notebooks/assessing_model_results.ipynb

@@ -0,0 +1,262 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Setup\n",
+    "\n",
+    "Make sure your virtualenv (use the same one as ml_api) is active, and all the imports below are installed\n",
+    "\n",
+    "Make sure your database docker container is running."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import sys\n",
+    "from sqlalchemy import create_engine"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Add the ptdraft folder path to the sys.path list\n",
+    "# WINDOWS USERS: You will need to change the backslashes (TODO: check if this is true)\n",
+    "sys.path.append('../../')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "A reminder that SQLAlchemy DB URIs look like this:\n",
+    "`postgres+psycop2://myuser:[email protected]:5432/mydatabase`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['/Users/christophersamiullah/repos/testing-and-monitoring-ml-deployments/exercise_notebooks', '/Users/christophersamiullah/repos/advanced_ml_deployment_draft/packages/ml_api/differential_tests', '/Users/christophersamiullah/repos/advanced_ml_deployment_draft/packages/ml_api', '/usr/local/bin/python3.7', '/usr/local/Cellar/python/3.7.4/Frameworks/Python.framework/Versions/3.7/lib/python37.zip', '/usr/local/Cellar/python/3.7.4/Frameworks/Python.framework/Versions/3.7/lib/python3.7', '/usr/local/Cellar/python/3.7.4/Frameworks/Python.framework/Versions/3.7/lib/python3.7/lib-dynload', '', '/Users/christophersamiullah/repos/testing-and-monitoring-ml-deployments/packages/ml_api/env/lib/python3.7/site-packages', '/Users/christophersamiullah/repos/testing-and-monitoring-ml-deployments/packages/ml_api/env/lib/python3.7/site-packages/IPython/extensions', '/Users/christophersamiullah/.ipython', '../', '..', '../../']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(sys.path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from packages.ml_api.api.config import DevelopmentConfig"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "postgresql+psycopg2://user:[email protected]:6609/ml_api_dev\n"
+     ]
+    }
+   ],
+   "source": [
+    "db_uri = DevelopmentConfig.SQLALCHEMY_DATABASE_URI\n",
+    "print(db_uri)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "engine = create_engine(db_uri)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lasso_model_df = pd.read_sql_table(\"regression_model_predictions\", con=engine)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gradient_model_df = pd.read_sql_table(\"gradient_boosting_model_predictions\", con=engine)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "combined_df = lasso_model_df.merge(gradient_model_df, how='outer')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>user_id</th>\n",
+       "      <th>datetime_captured</th>\n",
+       "      <th>model_version</th>\n",
+       "      <th>inputs</th>\n",
+       "      <th>outputs</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>007</td>\n",
+       "      <td>2019-12-21 10:15:22.064246+00:00</td>\n",
+       "      <td>0.0.4444</td>\n",
+       "      <td>[{\"1stFlrSF\": 896, \"2ndFlrSF\": 0, \"3SsnPorch\":...</td>\n",
+       "      <td>[105437.16948684008]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>34</td>\n",
+       "      <td>007</td>\n",
+       "      <td>2019-12-21 10:23:00.036615+00:00</td>\n",
+       "      <td>0.0.4444</td>\n",
+       "      <td>[{\"1stFlrSF\": 896, \"2ndFlrSF\": 0, \"3SsnPorch\":...</td>\n",
+       "      <td>[105437.16948684008]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>35</td>\n",
+       "      <td>007</td>\n",
+       "      <td>2019-12-21 11:07:31.731324+00:00</td>\n",
+       "      <td>0.0.4444</td>\n",
+       "      <td>[{\"1stFlrSF\": 896, \"2ndFlrSF\": 0, \"3SsnPorch\":...</td>\n",
+       "      <td>[105437.16948684008]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>36</td>\n",
+       "      <td>007</td>\n",
+       "      <td>2019-12-21 11:10:33.730662+00:00</td>\n",
+       "      <td>0.0.4444</td>\n",
+       "      <td>[{\"1stFlrSF\": 896, \"2ndFlrSF\": 0, \"3SsnPorch\":...</td>\n",
+       "      <td>[105437.16948684008]</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>37</td>\n",
+       "      <td>007</td>\n",
+       "      <td>2019-12-21 11:10:34.408394+00:00</td>\n",
+       "      <td>0.0.4444</td>\n",
+       "      <td>[{\"1stFlrSF\": 896, \"2ndFlrSF\": 0, \"3SsnPorch\":...</td>\n",
+       "      <td>[105437.16948684008]</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id user_id                datetime_captured model_version  \\\n",
+       "0   1     007 2019-12-21 10:15:22.064246+00:00      0.0.4444   \n",
+       "1  34     007 2019-12-21 10:23:00.036615+00:00      0.0.4444   \n",
+       "2  35     007 2019-12-21 11:07:31.731324+00:00      0.0.4444   \n",
+       "3  36     007 2019-12-21 11:10:33.730662+00:00      0.0.4444   \n",
+       "4  37     007 2019-12-21 11:10:34.408394+00:00      0.0.4444   \n",
+       "\n",
+       "                                              inputs               outputs  \n",
+       "0  [{\"1stFlrSF\": 896, \"2ndFlrSF\": 0, \"3SsnPorch\":...  [105437.16948684008]  \n",
+       "1  [{\"1stFlrSF\": 896, \"2ndFlrSF\": 0, \"3SsnPorch\":...  [105437.16948684008]  \n",
+       "2  [{\"1stFlrSF\": 896, \"2ndFlrSF\": 0, \"3SsnPorch\":...  [105437.16948684008]  \n",
+       "3  [{\"1stFlrSF\": 896, \"2ndFlrSF\": 0, \"3SsnPorch\":...  [105437.16948684008]  \n",
+       "4  [{\"1stFlrSF\": 896, \"2ndFlrSF\": 0, \"3SsnPorch\":...  [105437.16948684008]  "
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "combined_df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

exercise_notebooks/docker_exercise/Dockerfile

@@ -0,0 +1,26 @@
+FROM python:3.7-alpine
+WORKDIR /code
+
+# Set env vars required by Flask
+ENV FLASK_APP app.py
+ENV FLASK_RUN_HOST 0.0.0.0
+
+# Install gcc so Python packages such as MarkupSafe
+# and SQLAlchemy can compile speedups.
+RUN apk add --no-cache gcc musl-dev linux-headers
+
+# copy local requirements.txt into container
+# doing this separately from the main copy
+# operation makes more efficient use of docker
+# layer caching.
+COPY requirements.txt requirements.txt
+
+# install requirements inside the container
+RUN pip install -r requirements.txt
+
+# Copy the current directory . in the project
+# to the workdir . in the image
+COPY . .
+
+# Set the default command for the container to flask run
+CMD ["flask", "run"]

exercise_notebooks/docker_exercise/app.py

@@ -0,0 +1,25 @@
+import time
+
+import redis
+from flask import Flask
+
+app = Flask(__name__)
+cache = redis.Redis(host='redis', port=6379)
+
+
+def get_hit_count():
+    retries = 5
+    while True:
+        try:
+            return cache.incr('hits')
+        except redis.exceptions.ConnectionError as exc:
+            if retries == 0:
+                raise exc
+            retries -= 1
+            time.sleep(0.5)
+
+
+@app.route('/')
+def hello():
+    count = get_hit_count()
+    return f'Hello World! I have been seen {count} times.\n'

exercise_notebooks/docker_exercise/docker-compose.yml

@@ -0,0 +1,8 @@
+version: '3'
+services:
+  web:
+    build: .
+    ports:
+      - "5000:5000"
+  redis:
+    image: "redis:alpine"

exercise_notebooks/docker_exercise/requirements.txt

@@ -0,0 +1,2 @@
+flask>=1.1.1,<1.2.0
+redis>=3.3.11,<3.4