diff --git a/CHANGELOG.md b/CHANGELOG.md
index 44629bd9b80b9bfd6a8d6a991fe52c8ce5ed3919..a6b2de738c79b3ad38c6bf77a2abb3611a6511eb 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -14,6 +14,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed ###
+- `TableConverter` now converts int to float and vice versa to match the desired dtype.
+
### Deprecated ###
### Removed ###
diff --git a/src/caosadvancedtools/crawler.py b/src/caosadvancedtools/crawler.py
index 5d91d85cbbbff5b6f64ce9a9de1f29ca603d3b8a..87b91a52a6034e906766a56ded787416e5c0027d 100644
--- a/src/caosadvancedtools/crawler.py
+++ b/src/caosadvancedtools/crawler.py
@@ -279,6 +279,8 @@ class Crawler(object):
except DataInconsistencyError as e:
logger.debug(traceback.format_exc())
logger.debug(e)
+ # TODO: Generally: in which cases should exceptions be raised? When is
+ # errors_occured set to True? The expected behavior must be documented.
except Exception as e:
try:
DataModelProblems.evaluate_exception(e)
diff --git a/src/caosadvancedtools/table_importer.py b/src/caosadvancedtools/table_importer.py
index 0b55252bbf4d65cde1ffdf0711f396dda0f29546..654d28b41a8bd6fc2ad1d71b7deafa71e0ff21a0 100755
--- a/src/caosadvancedtools/table_importer.py
+++ b/src/caosadvancedtools/table_importer.py
@@ -205,27 +205,32 @@ def string_in_list(val, options, ignore_case=True):
return val
-class TableImporter(object):
+class TableImporter():
+ """Abstract base class for importing data from tables.
+ """
def __init__(self, converters, obligatory_columns=None, unique_keys=None,
datatypes=None):
"""
- converters: dict with column names as keys and converter functions as
- values
- This dict also defines what columns are required to exist
- throught the existing keys. The converter functions are
- applied to the cell values. They should also check for
- ValueErrors, such that a separate value check is not
- necessary.
- obligatory_columns: list of column names, optional
- each listed column must not have missing values
- unique_columns : list of column names that in
- combination must be unique; i.e. each row has a
- unique combination of values in those columns.
- datatypes: dict with column names as keys and datatypes as values
- All non-null values will be checked whether they have the
- provided datatype.
- This dict also defines what columns are required to exist
- throught the existing keys.
+ Parameters
+ ----------
+ converters : dict
+ Dict with column names as keys and converter functions as values. This dict also defines
+ what columns are required to exist throught the existing keys. The converter functions are
+ applied to the cell values. They should also check for ValueErrors, such that a separate
+ value check is not necessary.
+
+ obligatory_columns : list, optional
+ List of column names, each listed column must not have missing values.
+
+ unique_keys : list, optional
+ List of column names that in combination must be unique: each row has a unique
+ combination of values in those columns.
+
+ datatypes : dict, optional
+ Dict with column names as keys and datatypes as values. All non-null values will be
+ checked whether they have the provided datatype. This dict also defines what columns are
+ required to exist throught the existing keys.
+
"""
if converters is None:
@@ -247,11 +252,14 @@ class TableImporter(object):
raise NotImplementedError()
def check_columns(self, df, filename=None):
- """
- checks whether all required columns, i.e. columns for which converters
- were defined exist.
+ """Check whether all required columns exist.
+
+ Required columns are columns for which converters are defined.
+
+ Raises
+ ------
+ DataInconsistencyError
- Raises: DataInconsistencyError
"""
for col in self.required_columns:
@@ -267,12 +275,11 @@ class TableImporter(object):
raise DataInconsistencyError(errmsg)
def check_unique(self, df, filename=None):
- """
- Check whether value combinations that shall be unique for each row are
- unique.
+ """Check whether value combinations that shall be unique for each row are unique.
If a second row is found, that uses the same combination of values as a
previous one, the second one is removed.
+
"""
df = df.copy()
uniques = []
@@ -299,13 +306,33 @@ class TableImporter(object):
return df
- def check_datatype(self, df, filename=None):
- """
- Check for each column whether non-null fields are have the correct
- datatype.
- """
+ def check_datatype(self, df, filename=None, strict=False):
+ """Check for each column whether non-null fields have the correct datatype.
+
+ .. note::
+
+ If columns are float, but should be integer or vice versa, this method converts the
+ respective columns in place.
+ Parameters
+ ----------
+
+ strict: boolean, optional
+ If False (the default), try to convert columns, otherwise raise an error.
+
+ """
for key, datatype in self.datatypes.items():
+ # Check for castable numeric types first: We unconditionally cast float to int and vice
+ # versa, because CaosDB does not have different sizes anyway.
+ col_dtype = df.dtypes[key]
+ if not strict and not np.issubdtype(col_dtype, datatype):
+ issub = np.issubdtype
+ # These special cases should be fine.
+ if ((issub(col_dtype, np.integer) and issub(datatype, np.floating))
+ or (issub(col_dtype, np.floating) and issub(datatype, np.integer))):
+ df[key] = df[key].astype(datatype)
+
+ # Now check each element
for idx, val in df.loc[
pd.notnull(df.loc[:, key]), key].iteritems():
@@ -326,6 +353,11 @@ class TableImporter(object):
Check in each row whether obligatory fields are empty or null.
Rows that have missing values are removed.
+
+ Returns
+ -------
+ out : pandas.DataFrame
+ The input DataFrame with incomplete rows removed.
"""
df = df.copy()
@@ -362,10 +394,26 @@ class TableImporter(object):
return df
- def check_dataframe(self, df, filename):
+ def check_dataframe(self, df, filename=None, strict=False):
+ """Check if the dataframe conforms to the restrictions.
+
+ Checked restrictions are: Columns, data types, uniqueness requirements.
+
+ Parameters
+ ----------
+
+ df: pandas.DataFrame
+ The dataframe to be checked.
+
+ filename: string, optional
+ The file name, only used for output in case of problems.
+
+ strict: boolean, optional
+ If False (the default), try to convert columns, otherwise raise an error.
+ """
self.check_columns(df, filename=filename)
df = self.check_missing(df, filename=filename)
- self.check_datatype(df, filename=filename)
+ self.check_datatype(df, filename=filename, strict=strict)
if len(self.unique_keys) > 0:
df = self.check_unique(df, filename=filename)
@@ -378,8 +426,7 @@ class XLSImporter(TableImporter):
return self.read_xls(filename=filename, **kwargs)
def read_xls(self, filename, **kwargs):
- """
- converts an xls file into a Pandas DataFrame.
+ """Convert an xls file into a Pandas DataFrame.
The converters of the XLSImporter object are used.
diff --git a/unittests/data/datatypes.xlsx b/unittests/data/datatypes.xlsx
new file mode 100644
index 0000000000000000000000000000000000000000..34fc4cf43092a68b630e0e04ebc43609b8a0b17b
Binary files /dev/null and b/unittests/data/datatypes.xlsx differ
diff --git a/unittests/test_table_importer.py b/unittests/test_table_importer.py
index 9c8a379d8c12def32c04cf82c5e09c0f5f6f175c..f2727472798c9605313c3f4aacc4755530a6862d 100644
--- a/unittests/test_table_importer.py
+++ b/unittests/test_table_importer.py
@@ -23,7 +23,6 @@ import unittest
from functools import partial
from tempfile import NamedTemporaryFile
-import caosdb as db
import numpy as np
import pandas as pd
import pytest
@@ -211,6 +210,21 @@ class XLSImporterTest(TableImporterTest):
self.assertRaises(DataInconsistencyError, importer.read_xls,
tmp.name)
+ def test_datatypes(self):
+ """Test datataypes in columns."""
+ importer = XLSImporter(converters={},
+ obligatory_columns=["float_as_float"],
+ datatypes={
+ "float_as_float": float,
+ "int_as_float": float,
+ "int_as_int": int,
+ "float_as_int": int,
+ }
+ )
+ df = importer.read_xls(os.path.join(os.path.dirname(__file__), "data", "datatypes.xlsx"))
+ assert np.issubdtype(df.loc[0, "int_as_float"], float)
+ assert df.loc[1, "float_as_int"] == 6 # This is an acceptable rounding error.
+
class CSVImporterTest(TableImporterTest):
def test_full(self):