adding industry and urbanization datasets

cities/utils/clean_industry.py

@@ -0,0 +1,97 @@
+import numpy as np
+import pandas as pd
+
+from cities.utils.cleaning_utils import standardize_and_scale
+from cities.utils.data_grabber import DataGrabber
+
+
+def clean_industry():
+    data = DataGrabber()
+    data.get_features_wide(["gdp"])
+    gdp = data.wide["gdp"]
+
+    industry = pd.read_csv("../data/raw/ACSDP5Y2021_DP03_industry.csv")
+
+    assert industry["GEO_ID"].isna() == 0
+
+    industry["GEO_ID"] = industry["GEO_ID"].str.split("US").str[1]
+    industry["GEO_ID"] = industry["GEO_ID"].astype("int64")
+    industry = industry.rename(columns={"GEO_ID": "GeoFIPS"})
+
+    common_fips = np.intersect1d(gdp["GeoFIPS"].unique(), industry["GeoFIPS"].unique())
+
+    industry = industry[industry["GeoFIPS"].isin(common_fips)]
+
+    industry = industry.merge(gdp[["GeoFIPS", "GeoName"]], on="GeoFIPS", how="left")
+
+    industry = industry[
+        [
+            "GeoFIPS",
+            "GeoName",
+            "DP03_0004E",
+            "DP03_0033E",
+            "DP03_0034E",
+            "DP03_0035E",
+            "DP03_0036E",
+            "DP03_0037E",
+            "DP03_0038E",
+            "DP03_0039E",
+            "DP03_0040E",
+            "DP03_0041E",
+            "DP03_0042E",
+            "DP03_0043E",
+            "DP03_0044E",
+            "DP03_0045E",
+        ]
+    ]
+
+    column_name_mapping = {
+        "DP03_0004E": "employed_sum",
+        "DP03_0033E": "agri_forestry_mining",
+        "DP03_0034E": "construction",
+        "DP03_0035E": "manufacturing",
+        "DP03_0036E": "wholesale_trade",
+        "DP03_0037E": "retail_trade",
+        "DP03_0038E": "transport_utilities",
+        "DP03_0039E": "information",
+        "DP03_0040E": "finance_real_estate",
+        "DP03_0041E": "prof_sci_mgmt_admin",
+        "DP03_0042E": "education_health",
+        "DP03_0043E": "arts_entertainment",
+        "DP03_0044E": "other_services",
+        "DP03_0045E": "public_admin",
+    }
+
+    industry.rename(columns=column_name_mapping, inplace=True)
+
+    industry = industry.sort_values(by=["GeoFIPS", "GeoName"])
+
+    industry.to_csv("../data/raw/industry_absolute.csv", index=False)
+
+    row_sums = industry.iloc[:, 3:].sum(axis=1)
+
+    industry.iloc[:, 3:] = industry.iloc[:, 3:].div(row_sums, axis=0)
+    industry = industry.drop(["employed_sum"], axis=1)
+
+    industry_wide = industry.copy()
+
+    industry_long = pd.melt(
+        industry,
+        id_vars=["GeoFIPS", "GeoName"],
+        var_name="Category",
+        value_name="Value",
+    )
+
+    industry_std_wide = standardize_and_scale(industry)
+
+    industry_std_long = pd.melt(
+        industry_std_wide.copy(),
+        id_vars=["GeoFIPS", "GeoName"],
+        var_name="Category",
+        value_name="Value",
+    )
+
+    industry_wide.to_csv("../data/processed/industry_wide.csv", index=False)
+    industry_long.to_csv("../data/processed/industry_long.csv", index=False)
+    industry_std_wide.to_csv("../data/processed/industry_std_wide.csv", index=False)
+    industry_std_long.to_csv("../data/processed/industry_std_long.csv", index=False)

cities/utils/clean_urbanization.py

@@ -0,0 +1,70 @@
+import numpy as np
+import pandas as pd
+
+from cities.utils.cleaning_utils import standardize_and_scale
+from cities.utils.data_grabber import DataGrabber
+
+
+def clean_urbanization():
+    data = DataGrabber()
+    data.get_features_wide(["gdp"])
+    gdp = data.wide["gdp"]
+
+    dtype_mapping = {"STATE": str, "COUNTY": str}
+    urbanization = pd.read_csv("../data/raw/2020_UA_COUNTY.csv", dtype=dtype_mapping)
+
+    urbanization["GeoFIPS"] = urbanization["STATE"].astype(str) + urbanization[
+        "COUNTY"
+    ].astype(str)
+    urbanization["GeoFIPS"] = urbanization["GeoFIPS"].astype(int)
+
+    common_fips = np.intersect1d(
+        gdp["GeoFIPS"].unique(), urbanization["GeoFIPS"].unique()
+    )
+
+    urbanization = urbanization[urbanization["GeoFIPS"].isin(common_fips)]
+
+    urbanization = urbanization.merge(
+        gdp[["GeoFIPS", "GeoName"]], on="GeoFIPS", how="left"
+    )
+
+    urbanization = urbanization[
+        [
+            "GeoFIPS",
+            "GeoName",
+            "POPDEN_RUR",
+            "POPDEN_URB",
+            "HOUDEN_COU",
+            "HOUDEN_RUR",
+            "ALAND_PCT_RUR",
+        ]
+    ]
+
+    urbanization = urbanization.sort_values(by=["GeoFIPS", "GeoName"])
+
+    urbanization_wide = urbanization.copy()
+
+    urbanization_long = pd.melt(
+        urbanization,
+        id_vars=["GeoFIPS", "GeoName"],
+        var_name="Category",
+        value_name="Value",
+    )
+
+    urbanization_std_wide = standardize_and_scale(urbanization)
+
+    urbanization_std_long = pd.melt(
+        urbanization_std_wide.copy(),
+        id_vars=["GeoFIPS", "GeoName"],
+        var_name="Category",
+        value_name="Value",
+    )
+
+    urbanization_wide.to_csv("../data/processed/urbanization_wide.csv", index=False)
+    urbanization_long.to_csv("../data/processed/urbanization_long.csv", index=False)
+    urbanization_std_wide.to_csv(
+        "../data/processed/urbanization_std_wide.csv", index=False
+    )
+    urbanization_std_long.to_csv(
+        "../data/processed/urbanization_std_long.csv", index=False
+    )

cities/utils/cleaning_pipeline.py

@@ -1,10 +1,12 @@
 from cities.utils.clean_ethnic_composition import clean_ethnic_composition
 from cities.utils.clean_gdp import clean_gdp
+from cities.utils.clean_industry import clean_industry
 from cities.utils.clean_population import clean_population
 from cities.utils.clean_spending_commerce import clean_spending_commerce
 from cities.utils.clean_spending_HHS import clean_spending_HHS
 from cities.utils.clean_spending_transportation import clean_spending_transportation
 from cities.utils.clean_transport import clean_transport
+from cities.utils.clean_urbanization import clean_urbanization
 
 clean_gdp()
 
@@ -19,3 +21,7 @@
 clean_spending_HHS()
 
 clean_ethnic_composition()
+
+clean_industry()
+
+clean_urbanization()