pyreadstat 1.2.6__cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl → 1.2.8__cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl

pyreadstat/__init__.py

@@ -16,9 +16,11 @@
 
 from .pyreadstat import read_sas7bdat, read_xport, read_dta, read_sav, read_por, read_sas7bcat
 from .pyreadstat import write_sav, write_dta, write_xport, write_por
-from .pyreadstat import set_value_labels, set_catalog_to_sas
+#from .pyreadstat import set_value_labels, set_catalog_to_sas
+#from .pyreadstat import  set_catalog_to_sas
 from .pyreadstat import read_file_in_chunks, read_file_multiprocessing
 from ._readstat_parser import ReadstatError, metadata_container
+from .pyfunctions import set_value_labels, set_catalog_to_sas
 
-__version__ = "1.2.6"
+__version__ = "1.2.8"
 

pyreadstat/pyfunctions.py

@@ -0,0 +1,115 @@
+"""
+Functions written in pure python
+"""
+from copy import deepcopy
+
+import pandas as pd
+
+# Functions to deal with value labels
+
+def set_value_labels(dataframe, metadata, formats_as_category=True, formats_as_ordered_category=False):
+    """
+    Changes the values in the dataframe according to the value formats in the metadata.
+    It will return a copy of the dataframe. If no appropiate formats were found, the result will be an unchanged copy
+    of the original dataframe.
+
+    Parameters
+    ----------
+        dataframe : pandas dataframe
+            resulting from parsing a file
+        metadata : dictionary
+            resulting from parsing a file
+        formats_as_category : bool, optional
+            defaults to True. If True the variables having formats will be transformed into pandas categories.
+        formats_as_ordered_category : bool, optional
+            defaults to False. If True the variables having formats will be transformed into pandas ordered categories.
+            it has precedence over formats_as_category, meaning if this is True, it will take effect irrespective of
+            the value of formats_as_category.
+
+    Returns
+    -------
+        df_copy : pandas dataframe
+            a copy of the original dataframe with the values changed, if appropiate formats were found, unaltered
+            otherwise
+    """
+
+    df_copy = dataframe.copy()
+
+    if metadata.value_labels and metadata.variable_to_label:
+        for var_name, label_name in metadata.variable_to_label.items():
+            labels = metadata.value_labels.get(label_name)
+            if labels:
+                if var_name in df_copy.columns:
+                    df_copy[var_name] = df_copy[var_name].apply(lambda x: labels.get(x, x))
+                    if formats_as_ordered_category:
+                        categories = list(set(labels.values()))
+                        original_values = list(labels.keys())
+                        original_values.sort()
+                        revdict= dict()
+                        for orival in original_values:
+                            curcat = labels.get(orival)
+                            if not revdict.get(curcat):
+                                revdict[curcat] = orival
+                        categories.sort(key=revdict.get)
+                        df_copy[var_name] = pd.Categorical(
+                            df_copy[var_name],
+                            ordered = True,
+                            categories = categories
+                        )
+                    elif formats_as_category:
+                        df_copy[var_name] = df_copy[var_name].astype("category")
+
+
+    return df_copy
+
+def set_catalog_to_sas(sas_dataframe, sas_metadata, catalog_metadata, formats_as_category=True,  
+                       formats_as_ordered_category=False):
+    """
+    Changes the values in the dataframe and sas_metadata according to the formats in the catalog.
+    It will return a copy of the dataframe and metadata. If no appropriate formats were found, the result will
+    be an unchanged copy of the original dataframe.
+
+    Parameters
+    ----------
+        sas_dataframe : pandas dataframe
+            resulting from parsing a sas7bdat file
+        sas_metadata : pyreadstat metadata object
+            resulting from parsing a sas7bdat file
+        catalog_metadata : pyreadstat metadata object
+            resulting from parsing a sas7bcat (catalog) file
+        formats_as_category : bool, optional
+            defaults to True. If True the variables having formats will be transformed into pandas categories.
+        formats_as_ordered_category : bool, optional
+            defaults to False. If True the variables having formats will be transformed into pandas ordered categories.
+            it has precedence over formats_as_category, meaning if this is True, it will take effect irrespective of
+            the value of formats_as_category.
+
+    Returns
+    -------
+        df_copy : pandas dataframe
+            a copy of the original dataframe with the values changed, if appropriate formats were found, unaltered
+            otherwise
+        metadata : dict
+            a copy of the original sas_metadata enriched with catalog information if found, otherwise unaltered
+    """
+
+    if catalog_metadata.value_labels and sas_metadata.variable_to_label:
+        catalog_metadata_copy = deepcopy(catalog_metadata)
+        metadata = deepcopy(sas_metadata)
+        metadata.value_labels = catalog_metadata_copy.value_labels
+        df_copy = set_value_labels(sas_dataframe, metadata, formats_as_category=formats_as_category,
+                                   formats_as_ordered_category=formats_as_ordered_category)
+
+        variable_value_labels = dict()
+        for var_name, var_label in metadata.variable_to_label.items():
+            current_labels = catalog_metadata_copy.value_labels.get(var_label)
+            if current_labels:
+                variable_value_labels[var_name] = current_labels
+        metadata.variable_value_labels = variable_value_labels
+
+    else:
+        df_copy = sas_dataframe.copy()
+        metadata = deepcopy(sas_metadata)
+
+    return df_copy, metadata
+

{pyreadstat-1.2.6.dist-info → pyreadstat-1.2.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyreadstat
-Version: 1.2.6
+Version: 1.2.8
 Summary: Reads and Writes SAS, SPSS and Stata files into/from pandas data frames.
 Home-page: https://github.com/Roche/pyreadstat
 Download-URL: https://github.com/Roche/pyreadstat/dist
@@ -16,7 +16,7 @@ Classifier: Topic :: Scientific/Engineering
 Classifier: Environment :: Console
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: pandas >=1.2.0
+Requires-Dist: pandas>=1.2.0
 
  A Python package to read and write SAS
 (sas7bdat, sas7bcat, xport/xpt), SPSS (sav, zsav, por) and Stata (dta) files into/from pandas data frames. It is a wrapper

pyreadstat-1.2.8.dist-info/RECORD

@@ -0,0 +1,11 @@
+pyreadstat-1.2.8.dist-info/WHEEL,sha256=IjQRalpktecrnjQ0mlgISGBVe9z7Fv6GdQT0dw4Gf_A,153
+pyreadstat-1.2.8.dist-info/LICENSE,sha256=Tjohfl1RlkuDoTF5ctnLvkGnr8TU27PEy7PhOHjRz5c,12903
+pyreadstat-1.2.8.dist-info/RECORD,,
+pyreadstat-1.2.8.dist-info/METADATA,sha256=HPwSGb59xY_-hzL38nXadw7IvwfWi8VrodMRVe88jsc,1048
+pyreadstat-1.2.8.dist-info/top_level.txt,sha256=7LlluhR4SADp00dJTEVpKMet_Jki7JHA6abJ-wu831E,11
+pyreadstat/pyreadstat.cpython-310-aarch64-linux-gnu.so,sha256=vKjm8joR164qzEFXTWM6UUyZ36G9WI5Q9HZdVc7pOIE,2895824
+pyreadstat/_readstat_parser.cpython-310-aarch64-linux-gnu.so,sha256=Ckb1iUbAri1IwhJSGHr7eBGhJK5_1IJZrGV1xndrc54,2869752
+pyreadstat/worker.py,sha256=DHA7KXzZ3KSUSiYrepD7RpABPSLCYDq3-hOcoaFNBaI,972
+pyreadstat/__init__.py,sha256=hXfWCvrlQQ6KwBgT4b33_1_YgUw0PBmJu-sRmZZGrJo,1232
+pyreadstat/pyfunctions.py,sha256=wnlWbD5o1knLWX28s9ve8jWWv_MFDUTQ7vQUiyNFYmk,5172
+pyreadstat/_readstat_writer.cpython-310-aarch64-linux-gnu.so,sha256=1SuxUbJbBmpjKYqdZeYjPPRfB1WhL8yCdAKJ2bHwr8k,3340704

{pyreadstat-1.2.6.dist-info → pyreadstat-1.2.8.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.42.0)
+Generator: setuptools (75.1.0)
 Root-Is-Purelib: false
 Tag: cp310-cp310-manylinux_2_17_aarch64
 Tag: cp310-cp310-manylinux2014_aarch64

pyreadstat-1.2.6.dist-info/RECORD

@@ -1,10 +0,0 @@
-pyreadstat/_readstat_writer.cpython-310-aarch64-linux-gnu.so,sha256=rfOrQ51Plgo8ci4ZoupMfB6oVspixXMVMx3vXZb1Wy4,3266328
-pyreadstat/__init__.py,sha256=71erHFOhrvYUKI3X8RA1l_bRBclqHTIEEb__WM1GS4w,1124
-pyreadstat/_readstat_parser.cpython-310-aarch64-linux-gnu.so,sha256=kq7tlapATc3zSf11GHw6mPwN1nMgzHBqQ1pCG_snTB0,2821816
-pyreadstat/pyreadstat.cpython-310-aarch64-linux-gnu.so,sha256=RQ4E-OsY73JnhIzwYoQLRzovoj5FGJiF1Oa99qPw-bs,3058024
-pyreadstat/worker.py,sha256=DHA7KXzZ3KSUSiYrepD7RpABPSLCYDq3-hOcoaFNBaI,972
-pyreadstat-1.2.6.dist-info/WHEEL,sha256=7-IJbjbL0nWUFP_cSrTULDrfI4l8JN0GBqGHPqza7ao,154
-pyreadstat-1.2.6.dist-info/top_level.txt,sha256=7LlluhR4SADp00dJTEVpKMet_Jki7JHA6abJ-wu831E,11
-pyreadstat-1.2.6.dist-info/LICENSE,sha256=Tjohfl1RlkuDoTF5ctnLvkGnr8TU27PEy7PhOHjRz5c,12903
-pyreadstat-1.2.6.dist-info/RECORD,,
-pyreadstat-1.2.6.dist-info/METADATA,sha256=wFNERS2Kh28D6cZzrKlzSjsY5eh1zRwwEj_Tx6KD4Hg,1049