Changed SDMX backend from pandasdmx to sdmx1 (#28)

bis-med-it · Jun 20, 2024 · cb21845 · cb21845
1 parent b228bf6
commit cb21845
Show file tree

Hide file tree

Showing 11 changed files with 1,246 additions and 648 deletions.
diff --git a/00_augmentation.qmd b/00_augmentation.qmd
@@ -20,7 +20,7 @@ warning: false
 from __future__ import annotations
 import numpy as np
 import pandas as pd
-import pandasdmx as sdmx
+
 from utils import show_doc
 ```
 
@@ -222,6 +222,8 @@ from gingado.utils import list_all_dataflows
 ```
 
 ```{python}
+#| warning: false
+
 dflows = list_all_dataflows()
 dflows
 ```

diff --git a/00_benchmark.qmd b/00_benchmark.qmd
@@ -19,7 +19,6 @@ warning: false
 from __future__ import annotations
 import numpy as np
 import pandas as pd
-import pandasdmx as sdmx
 from utils import show_doc
 from gingado.benchmark import ggdBenchmark, ClassificationBenchmark, RegressionBenchmark, TimeSeriesSplit, ShuffleSplit
 

diff --git a/00_utils.qmd b/00_utils.qmd
@@ -194,7 +194,7 @@ Or the user can search dataflows by their human-readable name instead of their c
 
 ```{python}
 
-dflows[dflows.str.contains('Interest rates', case=False)]
+dflows[dflows.str.contains('Interest rate', case=False)]
 ```
 
 The function `load_SDMX_data` is a convenience function that downloads data from SDMX sources (and any specific dataflows passed as arguments) if they match the key and parameters set by the user.

diff --git a/docs/augmentation.html b/docs/augmentation.html
diff --git a/docs/benchmark.html b/docs/benchmark.html
diff --git a/docs/search.json b/docs/search.json
diff --git a/docs/site_libs/bootstrap/bootstrap-dark.min.css b/docs/site_libs/bootstrap/bootstrap-dark.min.css
diff --git a/docs/site_libs/bootstrap/bootstrap.min.css b/docs/site_libs/bootstrap/bootstrap.min.css
diff --git a/docs/utils.html b/docs/utils.html
diff --git a/gingado/utils.py b/gingado/utils.py
@@ -1,4 +1,4 @@
-import pandasdmx as sdmx
+import sdmx
 import datetime
 import numpy as np
 import pandas as pd
@@ -135,7 +135,7 @@ def list_all_dataflows(
     dflows = {}
     for src in sources:
         try:
-            dflows[src] = sdmx.to_pandas(sdmx.Request(src).dataflow().dataflow)
+            dflows[src] = sdmx.to_pandas(sdmx.Client(src).dataflow().dataflow)
             dflows[src] = dflows[src].index if codes_only else dflows[src].index.reset_index()
         except:
             pass
@@ -165,15 +165,15 @@ def load_SDMX_data(
         A pandas DataFrame with data from SDMX or None if no data matches the sources, keys, and parameters.
     """
     data_sdmx = {}
-    for source in sources.keys():
-        src_conn = sdmx.Request(source)
+    for source in list(sources.keys()):
+        src_conn = sdmx.Client(source)
         src_dflows = src_conn.dataflow()
         if sources[source] == 'all':
             dflows = {k: v for k, v in src_dflows.dataflow.items()}
         else:
             dflows = {k: v for k, v in src_dflows.dataflow.items() if k in sources[source]}
-        for dflow in dflows.keys():
-            if verbose: print(f"Querying data from {source}'s dataflow '{dflow}' - {dflows[dflow].dict()['name']}...")
+        for dflow in list(dflows.keys()):
+            if verbose: print(f"Querying data from {source}'s dataflow '{dflow}' - {dflows[dflow]._name}...")
             try:
                 data = sdmx.to_pandas(src_conn.data(dflow, key=keys, params=params), datetime='TIME_PERIOD')
             except:

diff --git a/requirements.txt b/requirements.txt
@@ -1,6 +1,6 @@
 numpy>=1.21
 pandas>=1.3.5
-pandasdmx>=1.8.1
+sdmx1>=2.15.0
 scikit-learn>=1.0.2
 requests_cache>=0.9.1
 matplotlib>=3.5