R style columns

RELEASE_NOTES.md

@@ -1,6 +1,7 @@
 
 # Next Release
 
+- [#212](https://github.com/IAMconsortium/pyam/pull/212) Now natively support reading R-style data frames with year columns like "X2015"
 - [#202](https://github.com/IAMconsortium/pyam/pull/202) Extend the `df.rename()` function with a `check_duplicates (default True)` validation option
 - [#201](https://github.com/IAMconsortium/pyam/pull/201) Added native support for legends outside of plots with `pyam.plotting.OUTSIDE_LEGEND` with a tutorial
 - [#199](https://github.com/IAMconsortium/pyam/pull/199) Initializing an `IamDataFrame` accepts kwargs to fill or create from the data any missing required columns

pyam/core.py

@@ -57,13 +57,16 @@ class IamDataFrame(object):
         an instance of an TimeSeries or Scenario (requires `ixmp`),
         or pd.DataFrame or data file with IAMC-format data columns.
         A pd.DataFrame can have the required data as columns or index.
+        Support is provided additionally for R-style data columns for years,
+        like "X2015", etc.
     kwargs:
         if `value=col`, melt `col` to `value` and use `col` name as `variable`;
         else, mapping of columns required for an `IamDataFrame` to:
         - one column in `df`
         - multiple columns, which will be concatenated by pipe
         - a string to be used as value for this column
     """
+
     def __init__(self, data, **kwargs):
         """Initialize an instance of an IamDataFrame"""
         # import data from pd.DataFrame or read from source

pyam/utils.py

@@ -132,6 +132,24 @@ def format_data(df, **kwargs):
     if isinstance(df, pd.Series):
         df = df.to_frame()
 
+    # Check for R-style year columns, converting where necessary
+    def convert_r_columns(c):
+        try:
+            first = c[0]
+            second = c[1:]
+            if first == 'X':
+                try:
+                    #  bingo! was X2015 R-style, return the integer
+                    return int(second)
+                except:
+                    # nope, not an int, fall down to final return statement
+                    pass
+        except:
+            # not a string/iterable/etc, fall down to final return statement
+            pass
+        return c
+    df.columns = df.columns.map(convert_r_columns)
+
     # if `value` is given but not `variable`,
     # melt value columns and use column name as `variable`
     if 'value' in kwargs and 'variable' not in kwargs:

tests/test_cast_to_iamc.py

@@ -79,3 +79,21 @@ def test_cast_with_variable_and_value(meta_df):
 
     assert compare(pe_df, df).empty
     pd.testing.assert_frame_equal(df.data, pe_df.data.reset_index(drop=True))
+
+
+def test_cast_from_r_df(test_pd_df):
+    df = test_pd_df.copy()
+    # last two columns are years
+    df.columns = list(df.columns[:-2]) + ['X{}'.format(c)
+                                          for c in df.columns[-2:]]
+    obs = IamDataFrame(df)
+    exp = IamDataFrame(test_pd_df)
+    assert compare(obs, exp).empty
+    pd.testing.assert_frame_equal(obs.data, exp.data)
+
+
+def test_cast_from_r_df_err(test_pd_df):
+    df = test_pd_df.copy()
+    # last two columns are years
+    df.columns = list(df.columns[:-2]) + ['Xfoo', 'Xbar']
+    pytest.raises(ValueError, IamDataFrame, df)