modified script in preprocess.py which downloads data and process

scripts/us_census/pep/population_estimate_by_race/README.md

@@ -1,14 +1,14 @@
 # US Census PEP: Population Estimate by Race
 
 ## About the Dataset
-This import includes the Population Count Estimates by Race for the United States from the year 1900 to 2020 on a yearly basis.
+This import includes the Population Count Estimates by Race for the United States from the year 1900 to 2023 on a yearly basis.
 
 The population is categorized by Race:
 AmericanIndianAndAlaskaNativeAlone,AsianAlone,BlackOrAfricanAmericanAlone,WhiteAlone,NativeHawaiianAndOtherPacificIslanderAlone
 
 
 ### Download URL
-The data in txt/csv formats are downloadable from within "https://www2.census.gov/programs-surveys/popest/tables" and "https://www2.census.gov/programs-surveys/popest/datasets". The actual URLs are listed in file_urls.json and file_url.txt(County data from 2020).
+The data in txt/csv formats are downloadable from within "https://www2.census.gov/programs-surveys/popest/tables" and "https://www2.census.gov/programs-surveys/popest/datasets". The actual URLs are listed in input_url.json.(County data from 2023).
 
 #### API Output
 These are the attributes that we will use
@@ -52,9 +52,7 @@ Run the test cases
 
 ### Import Procedure
 
-The below scripts will download the data
-`/bin/python3 scripts/us_census/pep/population_estimate_by_race/download.py`
-`sh scripts/us_census/pep/population_estimate_by_race/download1.sh`
+The below scripts will download the data and process and script will generate csv and mcf files.
+preprocess.py
+
 
-The below script will generate csv and mcf files.
-`/bin/python3 scripts/us_census/pep/population_estimate_by_race/preprocess.py`

scripts/us_census/pep/population_estimate_by_race/download.py

@@ -105,7 +105,7 @@ def _save_data(_url: str, download_local_path: str) -> None:
                 df = pd.read_csv(_url, on_bad_lines='skip', names=cols)
             df.to_excel(download_local_path + os.sep + file_name,\
                 index=False,engine='xlsxwriter')
-        elif "co-est00int-alldata" in _url or "CC-EST2020-ALLDATA" in _url:
+        elif "co-est00int-alldata" in _url or "CC-EST2020-ALLDATA" in _url or "cc-est2022-all":
             df = pd.read_csv(_url,
                              on_bad_lines='skip',
                              encoding='ISO-8859-1',
@@ -144,8 +144,16 @@ def _download(download_path: str, file_urls: list) -> None:
     """
     if not os.path.exists(download_path):
         os.mkdir(download_path)
+    all_files = os.listdir(download_path)
     for _url in file_urls:
-        _save_data(_url, download_path)
+        file_name = _url.split("/")[-1]
+        if not file_name in all_files:
+            try:
+                _save_data(_url, download_path)
+            except:
+                print(f"Unable to download {_url}")
+        else:
+            print(f"File already downloaded {file_name}")
 
 
 def main(_):

scripts/us_census/pep/population_estimate_by_race/file_urls.json

@@ -654,6 +654,8 @@
                 "https://www2.census.gov/programs-surveys/popest/datasets/2000-2010/intercensal/county/co-est00int-alldata-54.csv",
                 "https://www2.census.gov/programs-surveys/popest/datasets/2000-2010/intercensal/county/co-est00int-alldata-55.csv",
                 "https://www2.census.gov/programs-surveys/popest/datasets/2000-2010/intercensal/county/co-est00int-alldata-56.csv",
-                "https://www2.census.gov/programs-surveys/popest/datasets/2010-2020/counties/asrh/CC-EST2020-ALLDATA.csv"
+                "https://www2.census.gov/programs-surveys/popest/datasets/2010-2020/counties/asrh/CC-EST2020-ALLDATA.csv",
+                "https://www2.census.gov/programs-surveys/popest/datasets/2020-2023/counties/asrh/cc-est2023-alldata.csv"
                 ]
-}
+}
+