Modularization + Poetry + Docker (#213)

* reorg

* added configuration management; initial click cmds

* reset dirs completed

* major modularization effort

* prepping mbtiles

* first round of PR review updates

* round 2 of feedback review

* checkpoint

* habemus dockerfile 🎉

* updated dock-er-compose with long running container

* census generation works

* logging working

* updated README

* updated README

* last small update to README

* added instructions for log visualization

* census etl update for reusable fips module

* ejscreem etl updated

* further modularization

* score modularization

* tmp cleanup

score/ipython/ejscreen_etl.ipynb

@@ -8,33 +8,25 @@
    "outputs": [],
    "source": [
     "from pathlib import Path\n",
-    "import requests\n",
-    "import zipfile\n",
     "import numpy as np\n",
     "import pandas as pd\n",
     "import csv\n",
+    "import sys\n",
+    "import os\n",
     "\n",
-    "data_path = Path.cwd().parent / \"data\"\n",
-    "fips_csv_path = data_path / \"fips_states_2010.csv\"\n",
-    "csv_path = data_path / \"dataset\" / \"ejscreen_2020\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "67a58c24",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "download = requests.get(\n",
-    "    \"https://gaftp.epa.gov/EJSCREEN/2020/EJSCREEN_2020_StatePctile.csv.zip\",\n",
-    "    verify=False,\n",
-    ")\n",
-    "file_contents = download.content\n",
-    "zip_file_path = data_path / \"tmp\"\n",
-    "zip_file = open(zip_file_path / \"downloaded.zip\", \"wb\")\n",
-    "zip_file.write(file_contents)\n",
-    "zip_file.close()"
+    "module_path = os.path.abspath(os.path.join('..'))\n",
+    "if module_path not in sys.path:\n",
+    "    sys.path.append(module_path)\n",
+    "\n",
+    "from etl.sources.census.etl_utils import get_state_fips_codes\n",
+    "from utils import unzip_file_from_url, remove_all_from_dir\n",
+    "\n",
+    "DATA_PATH = Path.cwd().parent / \"data\"\n",
+    "TMP_PATH = DATA_PATH / \"tmp\"\n",
+    "EJSCREEN_FTP_URL = \"https://gaftp.epa.gov/EJSCREEN/2020/EJSCREEN_2020_StatePctile.csv.zip\"\n",
+    "EJSCREEN_CSV = TMP_PATH / \"EJSCREEN_2020_StatePctile.csv\"\n",
+    "CSV_PATH = DATA_PATH / \"dataset\" / \"ejscreen_2020\"\n",
+    "print(DATA_PATH)"
    ]
   },
   {
@@ -44,9 +36,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "with zipfile.ZipFile(zip_file_path / \"downloaded.zip\", \"r\") as zip_ref:\n",
-    "    zip_ref.extractall(zip_file_path)\n",
-    "ejscreen_csv = data_path / \"tmp\" / \"EJSCREEN_2020_StatePctile.csv\""
+    "# download file from ejscreen ftp\n",
+    "unzip_file_from_url(EJSCREEN_FTP_URL, TMP_PATH, TMP_PATH)"
    ]
   },
   {
@@ -58,7 +49,7 @@
    },
    "outputs": [],
    "source": [
-    "df = pd.read_csv(ejscreen_csv, dtype={\"ID\": \"string\"}, low_memory=False)"
+    "df = pd.read_csv(EJSCREEN_CSV, dtype={\"ID\": \"string\"}, low_memory=False)"
    ]
   },
   {
@@ -69,8 +60,8 @@
    "outputs": [],
    "source": [
     "# write nationwide csv\n",
-    "csv_path.mkdir(parents=True, exist_ok=True)\n",
-    "df.to_csv(csv_path / f\"usa.csv\", index=False)"
+    "CSV_PATH.mkdir(parents=True, exist_ok=True)\n",
+    "df.to_csv(CSV_PATH / f\"usa.csv\", index=False)"
    ]
   },
   {
@@ -81,19 +72,11 @@
    "outputs": [],
    "source": [
     "# write per state csvs\n",
-    "with open(fips_csv_path) as csv_file:\n",
-    "    csv_reader = csv.reader(csv_file, delimiter=\",\")\n",
-    "    line_count = 0\n",
-    "\n",
-    "    for row in csv_reader:\n",
-    "        if line_count == 0:\n",
-    "            line_count += 1\n",
-    "        else:\n",
-    "            fips = row[0].strip()\n",
-    "            print(f\"Generating data{fips} csv\")\n",
-    "            df1 = df[df.ID.str[:2] == fips]\n",
-    "            # we need to name the file data01.csv for ogr2ogr csv merge to work\n",
-    "            df1.to_csv(csv_path / f\"data{fips}.csv\", index=False)"
+    "for fips in get_state_fips_codes(DATA_PATH):\n",
+    "    print(f\"Generating data{fips} csv\")\n",
+    "    df1 = df[df.ID.str[:2] == fips]\n",
+    "    # we need to name the file data01.csv for ogr2ogr csv merge to work\n",
+    "    df1.to_csv(CSV_PATH / f\"data{fips}.csv\", index=False)"
    ]
   },
   {
@@ -102,6 +85,17 @@
    "id": "81b977f8",
    "metadata": {},
    "outputs": [],
+   "source": [
+    "# cleanup\n",
+    "remove_all_from_dir(TMP_PATH)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6d4f74d7",
+   "metadata": {},
+   "outputs": [],
    "source": []
   }
  ],