fix for transport data url not working

data/temp_hard_coded/transport_data.csv

@@ -0,0 +1,123 @@
+country,number cars,average fuel efficiency
+AL,563106,0.4
+AR,21633587,0.758
+AU,18326236,0.753
+AT,7421647,0.634
+AZ,1330551,0.755
+BD,2879708,0.858
+BY,4192291,0.795
+BE,7330718,0.714
+BJ,469761,0.324
+BO,1711005,0.593
+BA,978229,0.863
+BW,653274,0.679
+BR,93867016,0.552
+BG,4031748,0.805
+CI,905537,0.689
+KH,3751715,0.364
+CM,758145,0.462
+CA,23923806,0.682
+CL,4960945,0.689
+CN,294694457,0.914
+CO,13477996,0.588
+CR,1991398,0.314
+HR,1996056,0.634
+CU,633369,0.957
+CY,650805,0.696
+CZ,7325789,0.83
+DK,3131673,0.671
+DO,3854038,0.737
+EC,1925368,0.583
+EG,8412673,0.775
+SV,1008080,0.519
+ER,72405,0.696
+EE,865040,0.873
+ET,708416,0.531
+FI,5217850,0.761
+FR,42363000,0.576
+GE,1126470,0.578
+DE,56622000,0.786
+GH,2066943,0.446
+GR,9489299,0.752
+GT,3250194,0.6
+HN,1694504,0.605
+HU,4022798,0.728
+IS,289501,0.598
+IN,210023289,0.885
+ID,128398594,0.692
+IR,30377065,0.751
+IQ,5775777,0.794
+IE,2573961,0.679
+IL,3239305,0.739
+IT,52581575,0.67
+JM,541316,0.757
+JP,81602046,0.825
+JO,1502420,0.708
+KZ,4383120,0.939
+KE,2979910,0.471
+KW,2001940,0.847
+KG,993000,0.722
+LV,803628,0.571
+LB,1866407,0.756
+LY,3553497,0.607
+LT,1391568,0.538
+LU,466472,0.332
+MY,27613120,0.703
+MT,358947,0.769
+MU,507676,0.745
+MX,40205671,0.649
+MN,841537,0.889
+ME,211219,0.766
+MA,3791469,0.712
+MZ,698864,0.432
+MM,6381136,0.634
+NA,371281,0.446
+NP,2339169,0.56
+NL,10757655,0.801
+NZ,3656300,0.551
+NE,436420,0.408
+NG,11733425,0.646
+MK,442962,0.785
+NO,3969612,0.602
+OM,1370913,0.792
+PK,18352500,0.711
+PA,1288573,0.636
+PY,1871947,0.069
+PE,5604789,0.597
+PH,9251565,0.722
+PL,27409106,0.843
+PT,6590094,0.633
+QA,1330487,0.818
+KR,25680967,0.837
+MD,894253,0.753
+RO,7014661,0.776
+RU,54014259,0.838
+SA,6895799,0.741
+SN,468051,0.611
+RS,2282401,0.845
+SG,933534,0.848
+SK,2606412,0.793
+SI,1468439,0.585
+SS,69647,0.349
+ES,32986384,0.647
+LK,6795469,0.523
+SD,1252740,0.408
+SR,228388,0.663
+SE,6102914,0.467
+CH,5980512,0.552
+SY,2396544,0.76
+TR,21090424,0.802
+TJ,439972,0.665
+TH,37338139,0.753
+TG,64118,0.227
+TT,831803,0.862
+TN,2015601,0.747
+UA,14433709,0.886
+AE,3391125,0.79
+GB,38388214,0.715
+TZ,2163623,0.424
+US,281312446,0.666
+UY,2342026,0.447
+VE,7999760,0.677
+VN,50666855,0.777
+ZW,1198584,0.777

scripts/prepare_transport_data_input.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 import logging
 import os
+import shutil
 from pathlib import Path
 
 import country_converter as coco
@@ -21,7 +22,16 @@ def download_number_of_vehicles():
     """
     fn = "https://apps.who.int/gho/athena/data/GHO/RS_194?filter=COUNTRY:*&ead=&x-sideaxis=COUNTRY;YEAR;DATASOURCE&x-topaxis=GHO&profile=crosstable&format=csv"
     storage_options = {"User-Agent": "Mozilla/5.0"}
-    Nbr_vehicles_csv = pd.read_csv(fn, storage_options=storage_options, encoding="utf8")
+
+    # Read the 'Data' sheet directly from the csv file at the provided URL
+    try:
+        Nbr_vehicles_csv = pd.read_csv(
+            fn, storage_options=storage_options, encoding="utf8"
+        )
+        print("File read successfully.")
+    except Exception as e:
+        print("Failed to read the file:", e)
+        return pd.DataFrame()
 
     Nbr_vehicles_csv = Nbr_vehicles_csv.rename(
         columns={
@@ -110,28 +120,34 @@ def download_CO2_emissions():
     # Downloaded and prepare CO2_emissions_csv:
     CO2_emissions_csv = download_CO2_emissions().copy()
 
-    # Join the DataFrames by the 'country' column
-    merged_df = pd.merge(vehicles_csv, CO2_emissions_csv, on="country")
-    merged_df = merged_df[["country", "number cars", "average fuel efficiency"]]
-
-    # drop rows with NaN values in 'average fuel efficiency'
-    merged_df = merged_df.dropna(subset=["average fuel efficiency"])
-
-    # Convert the 'average fuel efficiency' to float
-    merged_df["average fuel efficiency"] = merged_df["average fuel efficiency"].astype(
-        float
-    )
-
-    # Round the 'average fuel efficiency' to three decimal places
-    merged_df.loc[:, "average fuel efficiency"] = merged_df[
-        "average fuel efficiency"
-    ].round(3)
-
-    # Save
-    merged_df.to_csv(
-        snakemake.output.transport_data_input,
-        sep=",",
-        encoding="utf-8",
-        header="true",
-        index=False,
-    )
+    if vehicles_csv.empty or CO2_emissions_csv.empty:
+        # In case one of the urls is not working, we can use the hard-coded data
+        src = os.getcwd() + "/data/temp_hard_coded/transport_data.csv"
+        dest = snakemake.output.transport_data_input
+        shutil.copy(src, dest)
+    else:
+        # Join the DataFrames by the 'country' column
+        merged_df = pd.merge(vehicles_csv, CO2_emissions_csv, on="country")
+        merged_df = merged_df[["country", "number cars", "average fuel efficiency"]]
+
+        # Drop rows with NaN values in 'average fuel efficiency'
+        merged_df = merged_df.dropna(subset=["average fuel efficiency"])
+
+        # Convert the 'average fuel efficiency' to float
+        merged_df["average fuel efficiency"] = merged_df[
+            "average fuel efficiency"
+        ].astype(float)
+
+        # Round the 'average fuel efficiency' to three decimal places
+        merged_df.loc[:, "average fuel efficiency"] = merged_df[
+            "average fuel efficiency"
+        ].round(3)
+
+        # Save the merged DataFrame to a CSV file
+        merged_df.to_csv(
+            snakemake.output.transport_data_input,
+            sep=",",
+            encoding="utf-8",
+            header="true",
+            index=False,
+        )