travis county examples rework and update to years available

SVInsight/svi.py

@@ -166,12 +166,12 @@ def boundaries_data(self, boundary: str = 'bg', year: int = 2019, overwrite: boo
         :return: The boundary data as a GeoDataFrame.
         :rtype: gpd.GeoDataFrame
 
-        :raises ValueError: If the boundary type is invalid, the year is not between 2010 and 2022, or geoids not properly formatted.
+        :raises ValueError: If the boundary type is invalid, the year is not between 2013 and 2021, or geoids not properly formatted.
         """
 
         # Validate Variables
         self._validate_value(boundary, ['bg', 'tract'], 'boundary')
-        self._validate_value(year, [2010, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022], 'year')
+        self._validate_value(year, [2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021], 'year')
         self._validate_format(boundary, str, 'boundary')
         self._validate_format(year, int, 'year')
 
@@ -191,7 +191,7 @@ def _download(year, state, boundary):
                 Downloads a shapefile from a remote FTP server, extracts it, and returns the boundary shapefile as a GeoDataFrame.
 
                 Args:
-                    year (int): The year of the shapefile.
+                    year (int): The year of the shapefile. Valid options are from 2011 to 2021.
                     state (str): The state abbreviation.
                     boundary (str): The boundary type. Must be 'bg' or 'tract'
 
@@ -219,8 +219,11 @@ def _download(year, state, boundary):
                 # print('opened binary')
 
                 # Specify the URL of the file you want to download
-                url = f"https://www2.census.gov/geo/tiger/GENZ{year}/shp/{zipped_filename}"
-
+                if year >= 2014:
+                    url = f"https://www2.census.gov/geo/tiger/GENZ{year}/shp/{zipped_filename}"
+                elif year == 2013:
+                    url = f"https://www2.census.gov/geo/tiger/GENZ{year}/{zipped_filename}"
+
                 # Send a GET request to the URL
                 response = requests.get(url, stream=True)
 
@@ -233,7 +236,6 @@ def _download(year, state, boundary):
                             if chunk:
                                 file.write(chunk)
 
-
                 # Unzip the file
                 shutil.unpack_archive(zipped_dir, filename_dir)
                 # with zipfile.ZipFile(f"{zipped_dir}", 'r') as zip_ref:
@@ -301,24 +303,24 @@ def census_data(self, boundary: str = 'bg', year: int = 2019, interpolate: bool
 
         :param boundary: The boundary type to retrieve data for. Valid options are 'bg' (block group) and 'tract' (census tract).
         :type boundary: str
-        :param year: The year of the Census data to retrieve. Valid options are from 2010 to 2022.
+        :param year: The year of the Census data to retrieve. Valid options are from 2011 to 2021.
         :type year: int
-        :param interpolate: Whether to interpolate missing data. Defaults to True.
+        :param interpolate: Whether to interpolate missing data. Defaults to True. If year is before 2014, ignored and not-interpolated.
         :type interpolate: bool, optional
         :param verbose: Whether to display verbose output. Defaults to False.
         :type verbose: bool, optional
         :param overwrite: Whether to overwrite existing data. Defaults to False.
         :type overwrite: bool, optional
 
-        :raises ValueError: If the boundary type is invalid or the year is not between 2010 and 2022.
+        :raises ValueError: If the boundary type is invalid or the year is not between 2013 and 2021.
         :raises FileNotFoundError: If the shapefile for the specified boundary and year does not exist.
 
         :return: None
         :rtype: None
         """
         # Validate Variables
         self._validate_value(boundary, ['bg', 'tract'], 'boundary')
-        self._validate_value(year, [2010, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022], 'year')
+        self._validate_value(year, [2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021], 'year')
         self._validate_format(boundary, str, 'boundary')
         self._validate_format(year, int, 'year')
 
@@ -407,7 +409,7 @@ def add_variable(self, boundary: str, year: int, name:str, num: list, den: list
         :type description: str, optional
         
         :raises ValueError: If the variable name already exists.
-        :raises ValueError: If the boundary type is invalid or the year is not between 2010 and 2022.
+        :raises ValueError: If the boundary type is invalid or the year is not between 2013 and 2021.
         :raises FileNotFoundError: If the raw data file doesn't exist. Run the census_data method first.
         
         :return: None
@@ -416,7 +418,7 @@ def add_variable(self, boundary: str, year: int, name:str, num: list, den: list
 
         # Validate Variables
         self._validate_value(boundary, ['bg', 'tract'], 'boundary')
-        self._validate_value(year, [2010, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022], 'year')
+        self._validate_value(year, [2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021], 'year')
 
         # if name of variable already exists, raise error
         if name in self.all_vars_eqs:
@@ -528,7 +530,7 @@ def calculate_svi(self, config_file: str, boundary: str = 'bg', year: int = 2019
         :type year: int
 
         :returns: None
-        :raises ValueError: If the boundary type is invalid or the year is not between 2010 and 2022,
+        :raises ValueError: If the boundary type is invalid or the year is not between 2013 and 2021,
 
         This method reads a configuration file in YAML format, loads the raw data as a dataframe,
         calculates the SVI using two different methods, and saves the results to output files.
@@ -554,7 +556,7 @@ def calculate_svi(self, config_file: str, boundary: str = 'bg', year: int = 2019
         """
         # validate inputs
         self._validate_value(boundary, ['bg', 'tract'], 'boundary')
-        self._validate_value(year, [2010, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022], 'year')
+        self._validate_value(year, [2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021], 'year')
 
         # open the configuration file
         with open(os.path.join(self.variables, f"{config_file}.yaml")) as stream:
@@ -771,7 +773,7 @@ def plot_svi(self, plot_option: int, geopackages: list):
 
 
         :returns: matplotlib figure object
-        :raises ValueError: If the boundary type is invalid or the year is not between 2010 and 2022,
+        :raises ValueError: If the boundary type is invalid or the year is not between 2013 and 2021,
 
         
         This method quickly creates an example SVI plot either by itself or in a comparative format. The plot options and their required information can be found below.
@@ -1291,8 +1293,6 @@ def extract_number(col_name):
 
                 # fill in values of data frame
                 data_df.loc[fips, var] = interpolated_value
-                if fips == 484530006011:
-                    print(interpolated_value)
 
                 interpolated_output.append([f'{fips}', var, 'Interpolated'])
 
@@ -1534,6 +1534,8 @@ def _fill_holes(self, data_df, boundary, geoids, api_key, year, interpolate, ver
             pandas.DataFrame: The DataFrame with missing values filled.
 
         """
+        if year <= 2014:
+            interpolate = False
         # create output data file to save interpolated results
         interpolated_output=[]
 

Travis_County/Data/Travis_County_2013_bg_missing_values.csv

@@ -0,0 +1,105 @@
+484530001022,B25064_001E,Tract Filled
+484530002031,B25077_001E,County Filled
+484530006011,B25077_001E,County Filled
+484530006012,B25077_001E,County Filled
+484530006032,B25077_001E,Tract Filled
+484530006034,B25077_001E,Tract Filled
+484530006035,B25077_001E,Tract Filled
+484530006041,B25077_001E,Tract Filled
+484530006042,B25077_001E,Tract Filled
+484530006043,B25077_001E,Tract Filled
+484530015012,B25064_001E,Tract Filled
+484530016023,B25077_001E,Tract Filled
+484530016033,B25064_001E,Tract Filled
+484530016034,B25064_001E,Tract Filled
+484530016042,B25064_001E,Tract Filled
+484530016044,B25064_001E,Tract Filled
+484530017052,B25064_001E,Tract Filled
+484530017053,B25064_001E,Tract Filled
+484530017142,B25064_001E,Tract Filled
+484530017143,B25064_001E,Tract Filled
+484530017191,B25064_001E,Tract Filled
+484530017192,B25064_001E,Tract Filled
+484530017222,B25077_001E,Tract Filled
+484530017292,B25064_001E,Tract Filled
+484530017382,B25064_001E,Tract Filled
+484530017383,B25064_001E,Tract Filled
+484530017451,B25064_001E,Tract Filled
+484530017493,B25077_001E,Tract Filled
+484530017501,B25077_001E,Tract Filled
+484530017521,B25077_001E,Tract Filled
+484530017522,B25077_001E,Tract Filled
+484530017531,B25077_001E,County Filled
+484530017571,B25064_001E,Tract Filled
+484530017702,B25064_001E,Tract Filled
+484530017703,B25064_001E,Tract Filled
+484530017712,B25064_001E,Tract Filled
+484530017741,B25064_001E,Tract Filled
+484530017743,B25064_001E,Tract Filled
+484530017751,B25064_001E,Tract Filled
+484530017752,B25064_001E,Tract Filled
+484530017791,B25064_001E,Tract Filled
+484530017811,B25064_001E,Tract Filled
+484530017822,B25064_001E,Tract Filled
+484530017852,B25077_001E,Tract Filled
+484530017861,B25077_001E,Tract Filled
+484530017863,B25077_001E,Tract Filled
+484530018043,B25077_001E,Tract Filled
+484530018064,B25077_001E,Tract Filled
+484530018121,B25077_001E,Tract Filled
+484530018122,B25077_001E,Tract Filled
+484530018192,B25077_001E,Tract Filled
+484530018202,B25077_001E,Tract Filled
+484530018224,B25077_001E,Tract Filled
+484530018333,B25064_001E,Tract Filled
+484530018413,B25064_001E,Tract Filled
+484530018491,B25077_001E,County Filled
+484530018492,B25077_001E,County Filled
+484530018493,B25077_001E,County Filled
+484530018494,B25077_001E,County Filled
+484530018503,B25077_001E,Tract Filled
+484530018542,B25064_001E,Tract Filled
+484530018551,B25064_001E,Tract Filled
+484530018555,B25064_001E,Tract Filled
+484530018582,B25064_001E,Tract Filled
+484530018583,B25064_001E,Tract Filled
+484530018584,B25064_001E,Tract Filled
+484530018585,B25064_001E,Tract Filled
+484530018592,B25064_001E,Tract Filled
+484530018631,B25077_001E,Tract Filled
+484530018642,B25077_001E,Tract Filled
+484530019142,B25064_001E,Tract Filled
+484530019161,B25064_001E,County Filled
+484530019162,B25064_001E,County Filled
+484530019171,B25064_001E,County Filled
+484530019172,B25064_001E,County Filled
+484530019173,B25064_001E,County Filled
+484530019174,B25064_001E,County Filled
+484530019181,B25064_001E,Tract Filled
+484530019182,B25064_001E,Tract Filled
+484530019183,B25064_001E,Tract Filled
+484530019193,B25064_001E,Tract Filled
+484530020052,B25077_001E,Tract Filled
+484530021052,B25077_001E,Tract Filled
+484530021063,B25064_001E,Tract Filled
+484530021072,B25064_001E,Tract Filled
+484530022121,B25064_001E,County Filled
+484530023041,B25077_001E,Tract Filled
+484530023043,B25077_001E,Tract Filled
+484530023083,B25077_001E,Tract Filled
+484530023084,B25077_001E,Tract Filled
+484530023141,B25077_001E,Tract Filled
+484530023142,B25077_001E,Tract Filled
+484530023143,B25077_001E,Tract Filled
+484530023144,B25077_001E,Tract Filled
+484530023152,B25077_001E,Tract Filled
+484530023161,B25077_001E,County Filled
+484530023162,B25077_001E,County Filled
+484530023163,B25077_001E,County Filled
+484530023172,B25077_001E,Tract Filled
+484530024021,B25064_001E,Tract Filled
+484530024072,B25064_001E,Tract Filled
+484530024191,B25077_001E,County Filled
+484530024192,B25077_001E,County Filled
+484530024301,B25064_001E,Tract Filled
+484530025001,B25064_001E,Tract Filled