Merge pull request #3 from kfettich-forks/kf_issue6

adjusted docker container so it can run python cleaning scripts

Author: kfettich

Dockerfile

@@ -1,4 +1,4 @@
-FROM tiangolo/uwsgi-nginx-flask:python3.6-alpine3.7
+FROM tiangolo/uwsgi-nginx-flask:python3.7
 
 ENV LISTEN_PORT=5555
 EXPOSE 5555
@@ -13,9 +13,12 @@ WORKDIR /paws-data-pipeline/
 COPY . /paws-data-pipeline/
 
 RUN chmod 777 /paws-data-pipeline
+RUN apt-get update
+RUN apt-get install -y sqlite3 libsqlite3-dev
 
 # If you have additional requirements beyond Flask (which is included in the
 # base image), generate a requirements.txt file with pip freeze and uncomment
 # the next three lines.
-#COPY requirements.txt /
-#RUN pip install --no-cache-dir -r /requirements.txt
+
+COPY requirements.txt /
+RUN pip install --no-cache-dir -r /requirements.txt

load_paws_data.ipynb

@@ -26,9 +26,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'fuzzywuzzy'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-3-d9f2dce0983a>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mnumpy\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mre\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 5\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mfuzzywuzzy\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mfuzz\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'fuzzywuzzy'"
+     ]
+    }
+   ],
    "source": [
     "import sqlite3\n",
     "import pandas as pd\n",
@@ -1104,7 +1116,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.7.4"
   }
  },
  "nbformat": 4,

requirements.txt

@@ -1,218 +1,3 @@
-alabaster==0.7.12
-anaconda-client==1.7.2
-anaconda-navigator==1.9.7
-anaconda-project==0.8.3
-asn1crypto==0.24.0
-astroid==2.2.5
-astropy==3.2.1
-atomicwrites==1.3.0
-attrs==19.1.0
-Babel==2.7.0
-backcall==0.1.0
-backports.functools-lru-cache==1.5
-backports.os==0.1.1
-backports.shutil-get-terminal-size==1.0.0
-backports.tempfile==1.0
-backports.weakref==1.0.post1
-beautifulsoup4==4.7.1
-bitarray==0.9.3
-bkcharts==0.2
-bleach==3.1.0
-bokeh==1.2.0
-boto==2.49.0
-Bottleneck==1.2.1
-certifi==2019.6.16
-cffi==1.12.3
-chardet==3.0.4
-Click==7.0
-cloudpickle==1.2.1
-clyent==1.2.2
-colorama==0.4.1
-conda==4.8.0
-conda-build==3.18.9
-conda-package-handling==1.3.11
-conda-verify==3.4.2
-contextlib2==0.5.5
-cryptography==2.7
-cycler==0.10.0
-Cython==0.29.12
-cytoolz==0.10.0
-dask==2.1.0
-decorator==4.4.0
-defusedxml==0.6.0
-distributed==2.1.0
-docutils==0.14
-entrypoints==0.3
-et-xmlfile==1.0.1
-fastcache==1.1.0
-filelock==3.0.12
-findspark==1.3.0
-Flask==1.1.1
-future==0.17.1
-fuzzywuzzy==0.17.0
-gevent==1.4.0
-glob2==0.7
-gmpy2==2.0.8
-greenlet==0.4.15
-h5py==2.9.0
-heapdict==1.0.0
-html5lib==1.0.1
-idna==2.8
-imageio==2.5.0
-imagesize==1.1.0
-importlib-metadata==0.17
-ipykernel==5.1.1
-ipython==7.6.1
-ipython-genutils==0.2.0
-ipywidgets==7.5.0
-isort==4.3.21
-itsdangerous==1.1.0
-jdcal==1.4.1
-jedi==0.13.3
-jeepney==0.4
-Jinja2==2.10.1
-joblib==0.13.2
-json5==0.8.4
-jsonschema==3.0.1
-jupyter==1.0.0
-jupyter-client==5.3.1
-jupyter-console==6.0.0
-jupyter-core==4.5.0
-jupyterlab==1.0.2
-jupyterlab-server==1.0.0
-keyring==18.0.0
-kiwisolver==1.1.0
-lazy-object-proxy==1.4.1
-libarchive-c==2.8
-lief==0.9.0
-llvmlite==0.29.0
-locket==0.2.0
-lxml==4.3.4
-MarkupSafe==1.1.1
-matplotlib==3.1.0
-mccabe==0.6.1
-mistune==0.8.4
-mkl-fft==1.0.12
-mkl-random==1.0.2
-mkl-service==2.0.2
-mock==3.0.5
-more-itertools==7.0.0
-mpmath==1.1.0
-msgpack==0.6.1
-multipledispatch==0.6.0
-navigator-updater==0.2.1
-nbconvert==5.5.0
-nbformat==4.4.0
-networkx==2.3
-nltk==3.4.5
-nose==1.3.7
-notebook==6.0.0
-numba==0.44.1
-numexpr==2.6.9
-numpy==1.16.4
-numpydoc==0.9.1
-olefile==0.46
-openpyxl==2.6.2
-packaging==19.0
-pandas==0.24.2
-pandocfilters==1.4.2
-parso==0.5.0
-partd==1.0.0
-path.py==12.0.1
-pathlib2==2.3.4
-patsy==0.5.1
-pep8==1.7.1
-pexpect==4.7.0
-pickleshare==0.7.5
-Pillow==6.2.0
-pkginfo==1.5.0.1
-pluggy==0.12.0
-ply==3.11
-prometheus-client==0.7.1
-prompt-toolkit==2.0.9
-psutil==5.6.3
-psycopg2==2.7.6.1
-ptyprocess==0.6.0
-py==1.8.0
-py4j==0.10.7
-pycodestyle==2.5.0
-pycosat==0.6.3
-pycparser==2.19
-pycurl==7.43.0.3
-pyflakes==2.1.1
-Pygments==2.4.2
-pylint==2.3.1
-pymongo==3.8.0
-pyodbc==4.0.26
-pyOpenSSL==19.0.0
-pyparsing==2.4.0
-pyrsistent==0.14.11
-PySocks==1.7.0
-pyspark==2.4.4
-pytest==5.0.1
-pytest-arraydiff==0.3
-pytest-astropy==0.5.0
-pytest-doctestplus==0.3.0
-pytest-openfiles==0.3.2
-pytest-remotedata==0.3.1
-python-dateutil==2.8.0
-python-dotenv==0.10.3
-python-Levenshtein==0.12.0
-pytz==2019.1
-PyWavelets==1.0.3
-PyYAML==5.1.1
-pyzmq==18.0.0
-QtAwesome==0.5.7
-qtconsole==4.5.1
-QtPy==1.8.0
-requests==2.22.0
-rope==0.14.0
-ruamel-yaml==0.15.46
-scikit-image==0.15.0
-scikit-learn==0.21.2
-scipy==1.3.0
-seaborn==0.9.0
-SecretStorage==3.1.1
-selenium==3.141.0
-Send2Trash==1.5.0
-simplegeneric==0.8.1
-singledispatch==3.4.0.3
-six==1.12.0
-snowballstemmer==1.9.0
-sortedcollections==1.1.2
-sortedcontainers==2.1.0
-soupsieve==1.8
-Sphinx==2.1.2
-sphinxcontrib-applehelp==1.0.1
-sphinxcontrib-devhelp==1.0.1
-sphinxcontrib-htmlhelp==1.0.2
-sphinxcontrib-jsmath==1.0.1
-sphinxcontrib-qthelp==1.0.2
-sphinxcontrib-serializinghtml==1.1.3
-sphinxcontrib-websupport==1.1.2
-spyder==3.3.6
-spyder-kernels==0.5.1
-SQLAlchemy==1.3.5
-statsmodels==0.10.0
-sympy==1.4
-tables==3.5.2
-tblib==1.4.0
-terminado==0.8.2
-testpath==0.4.2
-toolz==0.10.0
-tornado==6.0.3
-tqdm==4.32.1
-traitlets==4.3.2
-unicodecsv==0.14.1
-urllib3==1.24.2
-wcwidth==0.1.7
-webencodings==0.5.1
-Werkzeug==0.15.4
-widgetsnbextension==3.5.0
-wrapt==1.11.2
-wurlitzer==1.0.2
-xlrd==1.2.0
-XlsxWriter==1.1.8
-xlwt==1.3.0
-zict==1.0.0
-zipp==0.5.1
+pandas==1.0.0
+numpy==1.18.1
+fuzzywuzzy==0.17.0