Adds National Risk Index data to ETL pipeline (#549)

* Adds dev dependencies to requirements.txt and re-runs black on codebase

* Adds test and code for national risk index etl, still in progress

* Removes test_data from .gitignore

* Adds test data to nation_risk_index tests

* Creates tests and ETL class for NRI data

* Adds tests for load() and transform() methods of NationalRiskIndexETL

* Updates README.md with info about the NRI dataset

* Adds to dos

* Moves tests and test data into a tests/ dir in national_risk_index

* Moves tmp_dir for tests into data/tmp/tests/

* Promotes fixtures to conftest and relocates national_risk_index tests:
The relocation of national_risk_index tests is necessary because tests 
can only use fixtures specified in conftests within the same package

* Fixes issue with df.equals() in test_transform()

* Files reformatted by black

* Commit changes to other files after re-running black

* Fixes unused import that caused lint checks to fail

* Moves tests/ directory to app root for data_pipeline

data/data-pipeline/data_pipeline/etl/constants.py

@@ -39,6 +39,11 @@ DATASET_LIST = [
         "module_dir": "cdc_places",
         "class_name": "CDCPlacesETL",
     },
+    {
+        "name": "national_risk_index",
+        "module_dir": "national_risk_index",
+        "class_name": "NationalRiskIndexETL",
+    },
 ]
 CENSUS_INFO = {
     "name": "census",

data/data-pipeline/data_pipeline/etl/sources/national_risk_index/README.md

@@ -0,0 +1,14 @@
+# FEMA National Risk Index
+
+## Description
+
+The [National Risk Index](https://www.fema.gov/flood-maps/products-tools/national-risk-index) is a new, online mapping application from FEMA that identifies communities most at risk to 18 natural hazards. This application visualizes natural hazard risk metrics and includes data about expected annual losses from natural hazards, social vulnerability and community resilience.
+
+The National Risk Index's interactive web maps are at the county and Census tract level and made available via geographic information system (GIS) services for custom analyses. For this project, we've utilized the NRI data collected at the Census tract level
+
+## Data Transformation Summary
+
+The following transformations were applied to the NRI data during the ETL process:
+
+- The `TRACTFIPS` column was renamed to `GEOID10_TRACT` to match the name of columns that hold the Census Tract FIPS code in other data sets
+- The NRI score values for each Census tract were applied to each of the Census block groups inside of that Census tract so that the unit of analysis would match that of other datasets like the American Communities Survey

data/data-pipeline/data_pipeline/etl/sources/national_risk_index/etl.py

@@ -0,0 +1,72 @@
+import pandas as pd
+
+from data_pipeline.etl.base import ExtractTransformLoad
+from data_pipeline.utils import get_module_logger
+
+logger = get_module_logger(__name__)
+
+
+class NationalRiskIndexETL(ExtractTransformLoad):
+    """ETL class for the FEMA National Risk Index dataset"""
+
+    def __init__(self):
+        self.NRI_FTP_URL = "https://nri-data-downloads.s3.amazonaws.com/NRI_Table_CensusTracts.zip"
+        self.INPUT_CSV = self.TMP_PATH / "NRI_Table_CensusTracts.csv"
+        self.OUTPUT_DIR = (
+            self.DATA_PATH / "dataset" / "national_risk_index_2020"
+        )
+        self.BLOCK_GROUP_CSV = (
+            self.DATA_PATH / "dataset" / "census_acs_2019" / "usa.csv"
+        )
+        self.df: pd.DataFrame
+
+    def extract(self) -> None:
+        """Unzips NRI dataset from the FEMA data source and writes the files
+        to the temporary data folder for use in the transform() method
+        """
+        logger.info("Downloading National Risk Index Data")
+        super().extract(
+            self.NRI_FTP_URL,
+            self.TMP_PATH,
+        )
+
+    def transform(self) -> None:
+        """Reads the unzipped data file into memory and applies the following
+        transformations to prepare it for the load() method:
+
+        - Renames the Census Tract column to match the other datasets
+        - Applies the NRI score for each Census Tract to the Census Block
+          Groups inside of that Tract
+        """
+        logger.info("Transforming National Risk Index Data")
+
+        NRI_TRACT_COL = "TRACTFIPS"  # Census Tract Column in NRI data
+        TRACT_COL = self.GEOID_TRACT_FIELD_NAME  # Census Tract column name
+        BLOCK_COL = self.GEOID_FIELD_NAME  # Census Block Group column name
+
+        # read in the unzipped csv from NRI data source then rename the
+        # Census Tract column for merging
+        df_nri = pd.read_csv(
+            self.INPUT_CSV,
+            dtype={NRI_TRACT_COL: "string"},
+            na_values=["None"],
+            low_memory=False,
+        )
+        df_nri.rename(columns={NRI_TRACT_COL: TRACT_COL}, inplace=True)
+
+        # get the full list of Census Block Groups from the ACS data
+        # and extract the Census Tract ID from each Block Group ID
+        df_acs = pd.read_csv(self.BLOCK_GROUP_CSV, dtype={BLOCK_COL: "string"})
+        df_acs[TRACT_COL] = df_acs[BLOCK_COL].str[0:11]
+        df_block_group = df_acs[[BLOCK_COL, TRACT_COL]]
+
+        # merge NRI data on the Census Tract ID so that each
+        # Block Group inherits the NRI score of its Census Tract
+        self.df = df_block_group.merge(df_nri, how="left", on=TRACT_COL)
+
+    def load(self) -> None:
+        """Writes the NRI data as a csv to the directory at self.OUTPUT_DIR"""
+        logger.info("Saving National Risk Index CSV")
+        # write nationwide csv
+        self.OUTPUT_DIR.mkdir(parents=True, exist_ok=True)
+        self.df.to_csv(self.OUTPUT_DIR / "usa.csv", index=False)

data/data-pipeline/data_pipeline/tests/conftest.py

@@ -0,0 +1,33 @@
+import os
+
+import pytest
+
+from data_pipeline.config import settings
+from data_pipeline.etl.base import ExtractTransformLoad
+
+TMP_DIR = settings.APP_ROOT / "data" / "tmp" / "tests"
+
+
+@pytest.fixture(scope="session")
+def mock_paths(tmp_path_factory) -> tuple:
+    """Creates new DATA_PATH and TMP_PATH that point to a temporary local
+    file structure that can be used to mock data folder during testing
+    """
+    # sets location of the temp directory inside the national_risk_index folder
+    os.environ["PYTEST_DEBUG_TEMPROOT"] = str(TMP_DIR)
+    TMP_DIR.mkdir(parents=True, exist_ok=True)
+    # creates DATA_PATH and TMP_PATH directories in temp directory
+    data_path = tmp_path_factory.mktemp("data", numbered=False)
+    tmp_path = data_path / "tmp"
+    tmp_path.mkdir()
+    return data_path, tmp_path
+
+
+@pytest.fixture
+def mock_etl(monkeypatch, mock_paths) -> None:
+    """Creates a mock version of the base ExtractTransformLoad class and resets
+    global the variables for DATA_PATH and TMP_PATH to the local mock_paths
+    """
+    data_path, tmp_path = mock_paths
+    monkeypatch.setattr(ExtractTransformLoad, "DATA_PATH", data_path)
+    monkeypatch.setattr(ExtractTransformLoad, "TMP_PATH", tmp_path)

data/data-pipeline/data_pipeline/tests/sources/national_risk_index/data/acs.csv

@@ -0,0 +1,11 @@
+GEOID10,POPULATION
+050070403001,1000
+050070403002,1500
+050010201001,1000
+050010201002,1500
+150070405001,2000
+150070405002,2250
+150010210101,2000
+150010210102,1500
+150010211011,1750
+150010211012,1500

data/data-pipeline/data_pipeline/tests/sources/national_risk_index/data/input.csv

@@ -0,0 +1,6 @@
+TRACT,TRACTFIPS,RISK_SCORE,RISK_RATNG,RISK_NPCTL
+40300,05007040300,10.492015,Very Low,15.3494
+20100,05001020100,14.705854,Relatively Low,36.725828
+40500,15007040500,10.234981,Very Low,13.997993
+21010,15001021010,21.537231,Relatively Moderate,59.488033
+21101,15001021101,19.434585,Relatively Low,53.392265

data/data-pipeline/data_pipeline/tests/sources/national_risk_index/data/output.csv

@@ -0,0 +1,11 @@
+GEOID10,GEOID10_TRACT,TRACT,RISK_SCORE,RISK_RATNG,RISK_NPCTL
+050070403001,05007040300,40300,10.492015,Very Low,15.3494
+050070403002,05007040300,40300,10.492015,Very Low,15.3494
+050010201001,05001020100,20100,14.705854,Relatively Low,36.725828
+050010201002,05001020100,20100,14.705854,Relatively Low,36.725828
+150070405001,15007040500,40500,10.234981,Very Low,13.997993
+150070405002,15007040500,40500,10.234981,Very Low,13.997993
+150010210101,15001021010,21010,21.537231,Relatively Moderate,59.488033
+150010210102,15001021010,21010,21.537231,Relatively Moderate,59.488033
+150010211011,15001021101,21101,19.434585,Relatively Low,53.392265
+150010211012,15001021101,21101,19.434585,Relatively Low,53.392265

data/data-pipeline/data_pipeline/tests/sources/national_risk_index/test_etl.py

@@ -0,0 +1,110 @@
+from pathlib import Path
+from shutil import copyfile
+
+import pandas as pd
+
+from data_pipeline.config import settings
+from data_pipeline.etl.sources.national_risk_index.etl import (
+    NationalRiskIndexETL,
+)
+
+DATA_DIR = (
+    settings.APP_ROOT / "tests" / "sources" / "national_risk_index" / "data"
+)
+
+
+def copy_data_files(src: Path, dst: Path) -> None:
+    """Copies test data from src Path to dst Path for use in testing
+
+    Args
+        src: pathlib.Path instance. The location of the source data file.
+        dst: pathlib.Path instance. Where to copy the source data file to.
+
+    Returns
+        None. This is a void function
+    """
+    if not dst.exists():
+        dst.parent.mkdir(parents=True, exist_ok=True)
+        copyfile(src, dst)
+        assert dst.exists()
+
+
+class TestNationalRiskIndexETL:
+    def test_init(self, mock_etl, mock_paths):
+        """Tests that the mock NationalRiskIndexETL class instance was
+        initiliazed correctly.
+
+        Validates the following conditions:
+        - self.DATA_PATH points to the "data" folder in the temp directory
+        - self.TMP_PATH points to the "data/tmp" folder in the temp directory
+        - self.INPUT_PATH points to the correct path in the temp directory
+        - self.OUTPUT_PATH points to the correct path in the temp directory
+        """
+        # setup
+        etl = NationalRiskIndexETL()
+        data_path, tmp_path = mock_paths
+        input_csv = tmp_path / "NRI_Table_CensusTracts.csv"
+        output_dir = data_path / "dataset" / "national_risk_index_2020"
+        # validation
+        assert etl.DATA_PATH == data_path
+        assert etl.TMP_PATH == tmp_path
+        assert etl.INPUT_CSV == input_csv
+        assert etl.OUTPUT_DIR == output_dir
+        assert etl.GEOID_FIELD_NAME == "GEOID10"
+        assert etl.GEOID_TRACT_FIELD_NAME == "GEOID10_TRACT"
+
+    def test_transform(self, mock_etl):
+        """Tests the transform() method for NationalRiskIndexETL
+
+        Validates the following conditions:
+        - The columns have been renamed correctly
+        - The values for each tract has been applied to each of the block
+          groups in that tract
+        """
+        # setup - copy sample data into tmp_dir
+        etl = NationalRiskIndexETL()
+        input_src = DATA_DIR / "input.csv"
+        input_dst = etl.INPUT_CSV
+        acs_src = DATA_DIR / "acs.csv"
+        acs_dst = DATA_DIR / etl.BLOCK_GROUP_CSV
+        for src, dst in [(input_src, input_dst), (acs_src, acs_dst)]:
+            copy_data_files(src, dst)
+        # setup - read in sample output as dataframe
+        TRACT_COL = etl.GEOID_TRACT_FIELD_NAME
+        BLOCK_COL = etl.GEOID_FIELD_NAME
+        expected = pd.read_csv(
+            DATA_DIR / "output.csv",
+            dtype={BLOCK_COL: "string", TRACT_COL: "string"},
+        )
+        # execution
+        etl.transform()
+        # validation
+        assert etl.df.shape == (10, 6)
+        assert etl.df.equals(expected)
+
+    def test_load(self, mock_etl):
+        """Tests the load() method for NationalRiskIndexETL
+
+        Validates the following conditions:
+        - The transformed dataframe is written to the directory specified by
+          self.OUTPUT_DIR
+        - The content of the file that's written matches the data in self.df
+        """
+        # setup
+        etl = NationalRiskIndexETL()
+        output_path = etl.OUTPUT_DIR / "usa.csv"
+        TRACT_COL = etl.GEOID_TRACT_FIELD_NAME
+        BLOCK_COL = etl.GEOID_FIELD_NAME
+        expected = pd.read_csv(
+            DATA_DIR / "output.csv",
+            dtype={BLOCK_COL: str, TRACT_COL: str},
+        )
+        etl.df = expected
+        # execution
+        etl.load()
+        output = pd.read_csv(
+            output_path, dtype={BLOCK_COL: str, TRACT_COL: str}
+        )
+        # validation
+        assert output_path.exists()
+        assert output.equals(expected)

data/data-pipeline/pyproject.toml

@@ -68,6 +68,9 @@ disable = [
 [tool.pylint.FORMAT]
 max-line-length = 150
 
+[tool.pylint.typecheck]
+generated-members = "pandas.*" # fixes E1101 for ETL.df 
+
 [tool.pylint.SIMILARITIES]
 # Configures how pylint detects repetitive code
 ignore-comments = "yes"

data/data-pipeline/requirements.txt

@@ -1,9 +1,14 @@
+appdirs==1.4.4; python_full_version >= "3.6.2"
 appnope==0.1.2; sys_platform == "darwin" and python_version >= "3.7" and platform_system == "Darwin"
 argcomplete==1.12.3; python_version < "3.8.0" and python_version >= "3.7"
 argon2-cffi==20.1.0; python_version >= "3.6"
+astroid==2.6.6; python_version >= "3.6" and python_version < "4.0"
 async-generator==1.10; python_full_version >= "3.6.1" and python_version >= "3.7"
+atomicwrites==1.4.0; python_version >= "3.6" and python_full_version < "3.0.0" and sys_platform == "win32" or sys_platform == "win32" and python_version >= "3.6" and python_full_version >= "3.4.0"
 attrs==21.2.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6"
 backcall==0.2.0; python_version >= "3.7"
+backports.entry-points-selectable==1.1.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "2.7"
+black==21.7b0; python_full_version >= "3.6.2"
 bleach==4.0.0; python_version >= "3.7"
 censusdata==1.15; python_version >= "2.7"
 certifi==2021.5.30; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.7"
@@ -12,21 +17,29 @@ charset-normalizer==2.0.4; python_full_version >= "3.6.0" and python_version >=
 click-plugins==1.1.1; python_version >= "3.6"
 click==8.0.1; python_version >= "3.6"
 cligj==0.7.2; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version < "4" and python_version >= "3.6"
-colorama==0.4.4; python_version >= "3.7" and python_full_version < "3.0.0" and platform_system == "Windows" and sys_platform == "win32" or platform_system == "Windows" and python_version >= "3.7" and python_full_version >= "3.5.0" and sys_platform == "win32"
+colorama==0.4.4; platform_system == "Windows" and python_version >= "3.7" and python_full_version >= "3.6.2" and sys_platform == "win32" and python_version < "4.0" and (python_version >= "3.7" and python_full_version < "3.0.0" and sys_platform == "win32" or sys_platform == "win32" and python_version >= "3.7" and python_full_version >= "3.5.0")
+configparser==5.0.2; python_version >= "3.6"
 cycler==0.10.0; python_version >= "3.7"
 debugpy==1.4.1; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
 decorator==5.0.9; python_version >= "3.7"
 defusedxml==0.7.1; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
+distlib==0.3.2; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
+dparse==0.5.1; python_version >= "3.5"
 dynaconf==3.1.4
 entrypoints==0.3; python_version >= "3.7"
+et-xmlfile==1.1.0; python_version >= "3.6"
+filelock==3.0.12; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
 fiona==1.8.20; python_version >= "3.6"
+flake8==3.9.2; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.5.0")
 geopandas==0.9.0; python_version >= "3.6"
 idna==3.2; python_version >= "3.5" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.5"
-importlib-metadata==4.6.3; python_version == "3.7"
+importlib-metadata==4.6.3; python_version == "3.7" and (python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.5.0" and python_version < "3.8" and python_version >= "3.6") and python_full_version >= "3.6.2" and (python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "3.8" or python_full_version >= "3.4.0" and python_version >= "3.6" and python_version < "3.8")
+iniconfig==1.1.1; python_version >= "3.6"
 ipykernel==6.1.0; python_version >= "3.7"
 ipython-genutils==0.2.0; python_version >= "3.7"
 ipython==7.26.0; python_version >= "3.7"
 ipywidgets==7.6.3
+isort==5.9.3; python_full_version >= "3.6.1" and python_version < "4.0" and python_version >= "3.6"
 jedi==0.18.0; python_version >= "3.7"
 jellyfish==0.6.1
 jinja2==3.0.1; python_version >= "3.7"
@@ -43,58 +56,80 @@ jupyter==1.0.0
 jupyterlab-pygments==0.1.2; python_version >= "3.7"
 jupyterlab-widgets==1.0.0; python_version >= "3.6"
 kiwisolver==1.3.1; python_version >= "3.7"
+lazy-object-proxy==1.6.0; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "4.0" or python_version >= "3.6" and python_version < "4.0" and python_full_version >= "3.6.0"
+liccheck==0.6.2; python_version >= "2.7"
 lxml==4.6.3; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
 markupsafe==2.0.1; python_version >= "3.7"
 matplotlib-inline==0.1.2; python_version >= "3.7"
 matplotlib==3.4.3; python_version >= "3.7"
+mccabe==0.6.1; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "4.0" or python_version >= "3.6" and python_version < "4.0" and python_full_version >= "3.5.0"
 mistune==0.8.4; python_version >= "3.7"
 munch==2.5.0; python_version >= "3.6"
+mypy-extensions==0.4.3; python_full_version >= "3.6.2" and python_version >= "3.5"
+mypy==0.910; python_version >= "3.5"
 nbclient==0.5.3; python_full_version >= "3.6.1" and python_version >= "3.7"
 nbconvert==6.1.0; python_version >= "3.7"
 nbformat==5.1.3; python_full_version >= "3.6.1" and python_version >= "3.7"
 nest-asyncio==1.5.1; python_full_version >= "3.6.1" and python_version >= "3.7"
 notebook==6.4.3; python_version >= "3.6"
 numpy==1.21.1; python_version >= "3.7"
-packaging==21.0; python_version >= "3.7"
+openpyxl==3.0.7; python_version >= "3.6"
+packaging==21.0; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
 pandas==1.3.1; python_full_version >= "3.7.1"
 pandocfilters==1.4.3; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.7"
 parso==0.8.2; python_version >= "3.7"
+pathspec==0.9.0; python_full_version >= "3.6.2"
 pexpect==4.8.0; sys_platform != "win32" and python_version >= "3.7"
 pickleshare==0.7.5; python_version >= "3.7"
 pillow==8.3.1; python_version >= "3.7"
+platformdirs==2.2.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6"
+pluggy==0.13.1; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.6"
 prometheus-client==0.11.0; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
 prompt-toolkit==3.0.19; python_full_version >= "3.6.1" and python_version >= "3.7"
 ptyprocess==0.7.0; sys_platform != "win32" and python_version >= "3.7" and os_name != "nt"
-py==1.10.0; python_version >= "3.6" and python_full_version < "3.0.0" and implementation_name == "pypy" or implementation_name == "pypy" and python_version >= "3.6" and python_full_version >= "3.4.0"
+py==1.10.0; python_version >= "3.6" and python_full_version < "3.0.0" and implementation_name == "pypy" or python_full_version >= "3.5.0" and python_version >= "3.6" and implementation_name == "pypy"
+pycodestyle==2.7.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
 pycparser==2.20; python_version >= "3.6" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.6"
+pyflakes==2.3.1; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
 pygments==2.9.0; python_version >= "3.7"
+pylint==2.9.6; python_version >= "3.6" and python_version < "4.0"
 pypandoc==1.6.3
 pyparsing==2.4.7; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.7"
 pyproj==3.1.0; python_version >= "3.7"
 pyrsistent==0.18.0; python_version >= "3.6"
+pytest==6.2.4; python_version >= "3.6"
 python-dateutil==2.8.2; python_full_version >= "3.7.1" and python_version >= "3.7"
 pytz==2021.1; python_full_version >= "3.7.1" and python_version >= "2.7"
 pywin32==301; sys_platform == "win32" and python_version >= "3.6"
 pywinpty==1.1.3; os_name == "nt" and python_version >= "3.6"
-pyyaml==5.4.1; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.6.0"
+pyyaml==5.4.1; python_version >= "3.5" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version >= "3.5"
 pyzmq==22.2.1; python_full_version >= "3.6.1" and python_version >= "3.7"
 qtconsole==5.1.1; python_version >= "3.6"
 qtpy==1.9.0; python_version >= "3.6"
+regex==2021.8.3; python_full_version >= "3.6.2"
 requests==2.26.0; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.6.0")
+safety==1.10.3; python_version >= "3.5"
+semantic-version==2.8.5; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "2.7"
 send2trash==1.8.0; python_version >= "3.6"
 shapely==1.7.1; python_version >= "3.6"
-six==1.16.0; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.7"
+six==1.16.0; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
 terminado==0.11.0; python_version >= "3.6"
 testpath==0.5.0; python_version >= "3.7"
+toml==0.10.2; python_version >= "3.6" and python_full_version < "3.0.0" and python_version < "4.0" or python_full_version >= "3.5.0" and python_version >= "3.6" and python_version < "4.0"
+tomli==1.2.1; python_version >= "3.6" and python_full_version >= "3.6.2"
 tornado==6.1; python_full_version >= "3.6.1" and python_version >= "3.7"
+tox==3.24.1; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.5.0")
 tqdm==4.62.0; (python_version >= "2.7" and python_full_version < "3.0.0") or (python_full_version >= "3.4.0")
 traitlets==5.0.5; python_full_version >= "3.6.1" and python_version >= "3.7"
+typed-ast==1.4.3; python_version < "3.8" and python_full_version >= "3.6.2" and python_version >= "3.6" and implementation_name == "cpython"
 types-requests==2.25.6
-typing-extensions==3.10.0.0; python_version < "3.8" and python_version >= "3.6"
+typing-extensions==3.10.0.0; python_version < "3.8" and python_full_version >= "3.6.2" and python_version >= "3.6"
 urllib3==1.26.6; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.6.0" and python_version < "4" and python_version >= "2.7"
 us==2.0.2
+virtualenv==20.7.2; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
 wcwidth==0.2.5; python_full_version >= "3.6.1" and python_version >= "3.7"
 webencodings==0.5.1; python_version >= "3.7"
 widgetsnbextension==3.5.1
+wrapt==1.12.1; python_version >= "3.6" and python_version < "4.0"
 xlsxwriter==2.0.0
 zipp==3.5.0; python_version < "3.8" and python_version >= "3.6"