Use root-file, not root as a filetype (#261)

* Fix up confusion in code with "root" and "root-file" use - make it all "root-file" to keep consistent.
* More spelling errors corrected

Author: gordonwatts

.vscode/settings.json

@@ -14,7 +14,9 @@
         "backend's",
         "backends",
         "backoff",
+        "bortles",
         "cacheme",
+        "caplog",
         "cernopendata",
         "codecov",
         "Comming",
@@ -25,6 +27,8 @@
         "dont",
         "fget",
         "fname",
+        "forkingshirtballs",
+        "forkit",
         "getenv",
         "gitlab",
         "giveup",
@@ -83,6 +87,7 @@
         "SXTYPE",
         "SXUSER",
         "tcut",
+        "thegoodplace",
         "Topo",
         "tqdm",
         "unittests",

servicex/config_default.yaml

@@ -27,8 +27,8 @@ default_return_data: parquet
 # Easy enough to add a new one here...
 backend_types:
   - type: xaod
-    return_data: root
+    return_data: root-file
   - type: uproot
     return_data: parquet
   - type: cms_run1_aod
-    return_data: root
+    return_data: root-file

servicex/data_conversions.py

@@ -24,14 +24,14 @@ def __init__(self, default_file_type: str):
         self._default_file_type = default_file_type
 
     async def convert_to_pandas(self, file: Path, file_type: Optional[str] = None):
-        """Convert to a pandas dataframe from data stored in a file of a particular file_type
+        """Convert to a pandas DataFrame from data stored in a file of a particular file_type
 
         Args:
             file (Path): Path to the file
             file_type (str): What the file contains (root, parquet, etc)
         """
         file_type = file_type if file_type is not None else self._default_file_type
-        if file_type == "root":
+        if file_type == "root-file":
             return await self._convert_root_to_pandas(file)
         elif file_type == "parquet":
             return await self._convert_parquet_to_pandas(file)
@@ -48,7 +48,7 @@ async def convert_to_awkward(self, file: Path, file_type: Optional[str] = None):
             file_type (str): What the file contains (root, parquet, etc)
         """
         file_type = file_type if file_type is not None else self._default_file_type
-        if file_type == "root":
+        if file_type == "root-file":
             return await self._convert_root_to_awkward(file)
         elif file_type == "parquet":
             return await self._convert_parquet_to_awkward(file)
@@ -59,10 +59,10 @@ async def convert_to_awkward(self, file: Path, file_type: Optional[str] = None):
             )
 
     def combine_pandas(self, dfs: Iterable[pd.DataFrame]) -> pd.DataFrame:
-        """Combine many pandas dataframes into a single one, in order.
+        """Combine many pandas DataFrame into a single one, in order.
 
         Args:
-            dfs (Iterable[pd.DataFrame]): The list of dataframes
+            dfs (Iterable[pd.DataFrame]): The list of DataFrames
         """
         return pd.concat(dfs)
 
@@ -84,7 +84,7 @@ async def _convert_root_to_pandas(self, file: Path):
 
         Returns:
 
-            DataFrame   A pandas dataframe
+            DataFrame   A pandas DataFrame
 
         Note:
 
@@ -113,7 +113,7 @@ async def _convert_parquet_to_pandas(self, file: Path):
 
         Returns:
 
-            DataFrame   A pandas dataframe
+            DataFrame   A pandas DataFrame
 
         Note:
 
@@ -138,14 +138,14 @@ async def _convert_root_to_awkward(self, file: Path):
 
         Returns:
 
-            DataFrame   A pandas dataframe
+            DataFrame   A pandas DataFrame
 
         Note:
 
             - Work is done on a second thread.
             - Awkward is only imported if this is called.
             - A LazyArray is returned, so it isn't completely loaded into memory. That also means
-              this will leak filehandles - as that has to be left open.
+              this will leak file handles - as that has to be left open.
 
         """
 
@@ -169,7 +169,7 @@ async def _convert_parquet_to_awkward(self, file: Path):
 
         Returns:
 
-            DataFrame   A pandas dataframe
+            DataFrame   A pandas DataFrame
 
         Note:
 

tests/test_data_conversions.py

@@ -16,24 +16,24 @@ def check_pandas_accessible(col):
 
 @pytest.mark.asyncio
 async def test_root_to_pandas(good_root_file_path):
-    df = await DataConverterAdaptor("root").convert_to_pandas(good_root_file_path)
+    df = await DataConverterAdaptor("root-file").convert_to_pandas(good_root_file_path)
     assert isinstance(df, pd.DataFrame)
     assert len(df) == 283458
     check_pandas_accessible(df["JetPt"])
 
 
 @pytest.mark.asyncio
 async def test_root_to_pandas_default(good_root_file_path):
-    df = await DataConverterAdaptor("root").convert_to_pandas(
-        good_root_file_path, "root"
+    df = await DataConverterAdaptor("root-file").convert_to_pandas(
+        good_root_file_path, "root-file"
     )
     assert isinstance(df, pd.DataFrame)
     assert len(df) == 283458
 
 
 @pytest.mark.asyncio
 async def test_parquet_to_pandas_non_default(good_uproot_file_path):
-    df = await DataConverterAdaptor("root").convert_to_pandas(
+    df = await DataConverterAdaptor("root-file").convert_to_pandas(
         good_uproot_file_path, "parquet"
     )
     assert isinstance(df, pd.DataFrame)
@@ -57,29 +57,29 @@ async def test_parquet_to_awkward(good_uproot_file_path):
 
 @pytest.mark.asyncio
 async def test_root_to_awkward(good_root_file_path):
-    df = await DataConverterAdaptor("root").convert_to_awkward(good_root_file_path)
+    df = await DataConverterAdaptor("root-file").convert_to_awkward(good_root_file_path)
     assert len(df["JetPt"]) == 283458
     check_awkward_accessible(df["JetPt"])  # type: ignore
 
 
 @pytest.mark.asyncio
 async def test_to_awkward_fail(good_root_file_path):
     with pytest.raises(ServiceXException):
-        await DataConverterAdaptor("root").convert_to_awkward(
-            good_root_file_path, "notreally"
+        await DataConverterAdaptor("root-file").convert_to_awkward(
+            good_root_file_path, "not-really"
         )
 
 
 @pytest.mark.asyncio
-async def test_to_panads_fail(good_root_file_path):
+async def test_to_pandas_fail(good_root_file_path):
     with pytest.raises(ServiceXException):
-        await DataConverterAdaptor("root").convert_to_pandas(
-            good_root_file_path, "notreally"
+        await DataConverterAdaptor("root-file").convert_to_pandas(
+            good_root_file_path, "not-really"
         )
 
 
 def test_combine_pandas_from_root(good_root_file_path):
-    "Load a dataframe from root files and make sure that they work when we ask them to combine"
+    "Load a DataFrame from root files and make sure that they work when we ask them to combine"
 
     def load_df():
         import uproot as uproot
@@ -91,14 +91,14 @@ def load_df():
     df1 = load_df()
     df2 = load_df()
 
-    combined = DataConverterAdaptor("root").combine_pandas([df1, df2])
+    combined = DataConverterAdaptor("root-file").combine_pandas([df1, df2])
 
     assert len(combined) == len(df1) + len(df2)
     check_pandas_accessible(combined["JetPt"])
 
 
 def test_combine_pandas_from_parquet(good_uproot_file_path):
-    "Load a dataframe from a parquet file and make sure they work when we ask them to combine"
+    "Load a DataFrame from a parquet file and make sure they work when we ask them to combine"
 
     def load_df():
         import pandas as pd
@@ -108,14 +108,14 @@ def load_df():
     df1 = load_df()
     df2 = load_df()
 
-    combined = DataConverterAdaptor("root").combine_pandas([df1, df2])
+    combined = DataConverterAdaptor("root-file").combine_pandas([df1, df2])
 
     assert len(combined) == len(df1) + len(df2)
     check_pandas_accessible(combined["JetPT"])
 
 
 def test_combine_awkward_from_root(good_root_file_path):
-    "Load a dataframe from root files and make sure that they work when we ask them to combine"
+    "Load a DataFrame from root files and make sure that they work when we ask them to combine"
 
     def load_df():
         import uproot as uproot
@@ -127,22 +127,22 @@ def load_df():
     df1 = load_df()
     df2 = load_df()
 
-    combined = DataConverterAdaptor("root").combine_awkward([df1, df2])
+    combined = DataConverterAdaptor("root-file").combine_awkward([df1, df2])
 
     assert len(combined) == len(df1) + len(df2)
     check_awkward_accessible(combined["JetPt"])  # type: ignore
 
 
 def test_combine_awkward_from_parquet(good_uproot_file_path):
-    "Load a dataframe from a parquet file and make sure they work when we ask them to combine"
+    "Load a DataFrame from a parquet file and make sure they work when we ask them to combine"
 
     def load_df():
         return ak.from_parquet(good_uproot_file_path)  # type: ignore
 
     df1 = load_df()
     df2 = load_df()
 
-    combined = DataConverterAdaptor("root").combine_awkward([df1, df2])
+    combined = DataConverterAdaptor("root-file").combine_awkward([df1, df2])
 
     assert len(combined) == len(df1) + len(df2)
     check_awkward_accessible(combined["JetPT"])  # type: ignore

tests/test_servicex_config.py

@@ -63,13 +63,13 @@ def test_returned_datatype_from_endpoint():
     assert x.get_default_returned_datatype("forkit") == "spoons"
 
 
-def test_defalt_config_has_default_return_datatype():
+def test_default_config_has_default_return_datatype():
     "Test default settings - default_returned_datatype"
     c = ConfigSettings("servicex", "servicex")
     assert c["default_return_data"].exists()
 
 
-def test_defalt_config_has_backend_types():
+def test_default_config_has_backend_types():
     c = ConfigSettings("servicex", "servicex")
     assert c["backend_types"].exists()
     count = 0
@@ -151,7 +151,7 @@ def test_sx_adaptor_settings_name_not_type(caplog):
     assert len(caplog.record_tuples) == 0
 
 
-def test_sx_adaptor_settings_name_worng(caplog):
+def test_sx_adaptor_settings_name_wrong(caplog):
     from confuse import Configuration
 
     c = Configuration("bogus", "bogus")