seabirdfilehandler 0.5.0__py3-none-any.whl → 0.5.2__py3-none-any.whl

seabirdfilehandler/__init__.py

@@ -5,3 +5,4 @@ from .cnvfile import *
 from .xmlfiles import *
 from .validation_modules import *
 from .file_collection import *
+from .geomar_ctd_file_parser import *

seabirdfilehandler/bottlefile.py

@@ -4,10 +4,6 @@ import pandas as pd
 import numpy as np
 import logging
 from seabirdfilehandler import DataFile
-from seabirdfilehandler.dataframe_meta_accessor import (
-    SeriesMetaAccessor,  # noqa: F401
-    DataFrameMetaAccessor,  # noqa: F401
-)
 
 logger = logging.getLogger(__name__)
 

seabirdfilehandler/bottlelogfile.py

@@ -3,10 +3,6 @@ import re
 import logging
 import pandas as pd
 from seabirdfilehandler import DataFile
-from seabirdfilehandler.dataframe_meta_accessor import (
-    SeriesMetaAccessor,  # noqa: F401
-    DataFrameMetaAccessor,  # noqa: F401
-)
 
 logger = logging.getLogger(__name__)
 

seabirdfilehandler/cnvfile.py

@@ -46,23 +46,24 @@ class CnvFile(DataFile):
     def __init__(
         self,
         path_to_file: Path | str,
+        only_header: bool = False,
         create_dataframe: bool = False,
         absolute_time_calculation: bool = False,
         event_log_column: bool = False,
         coordinate_columns: bool = False,
     ):
-        super().__init__(path_to_file)
+        super().__init__(path_to_file, only_header)
         self.validation_modules = self.obtaining_validation_modules()
         self.start_time = self.reading_start_time()
         self.parameters = Parameters(self.data, self.data_table_description)
         if create_dataframe:
             self.df = self.parameters.get_pandas_dataframe()
-            if absolute_time_calculation:
-                self.absolute_time_calculation()
-            if event_log_column:
-                self.add_station_and_event_column()
-            if coordinate_columns:
-                self.add_position_columns()
+        if absolute_time_calculation:
+            self.absolute_time_calculation()
+        if event_log_column:
+            self.add_station_and_event_column()
+        if coordinate_columns:
+            self.add_position_columns()
 
     def reading_start_time(
         self,

seabirdfilehandler/datafiles.py

@@ -1,8 +1,19 @@
 from pathlib import Path
 import xmltodict
 import pandas as pd
+import numpy as np
 import logging
 
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(name)s - [%(levelname)s] - %(message)s",
+    datefmt="%Y-%m-%d %H:%M:%S",
+    handlers=[
+        logging.FileHandler("filehandler.log"),
+        logging.StreamHandler(),
+    ],
+)
+
 logger = logging.getLogger(__name__)
 
 
@@ -193,7 +204,7 @@ class DataFile:
 
     def to_csv(
         self,
-        selected_columns: list | None = None,
+        data: pd.DataFrame | np.ndarray,
         with_header: bool = True,
         output_file_path: Path | str | None = None,
         output_file_name: str | None = None,
@@ -218,10 +229,6 @@ class DataFile:
         -------
 
         """
-        selected_columns = (
-            self.df.columns if selected_columns is None else selected_columns
-        )
-        df = self.df[selected_columns].reset_index(drop=True)
         new_file_path = self.define_output_path(
             output_file_path, output_file_name
         )
@@ -229,15 +236,15 @@ class DataFile:
             with open(new_file_path, "w") as file:
                 for line in self.header:
                     file.write(line)
-            df.to_csv(new_file_path, index=False, mode="a")
+        if isinstance(data, pd.DataFrame):
+            data.to_csv(new_file_path, index=False, mode="a")
         else:
-            df.to_csv(new_file_path, index=False, mode="w")
-        logger.info(f"Wrote file {self.path_to_file} to {new_file_path}.")
+            np.savetxt(new_file_path, data, delimiter=",")
 
     def selecting_columns(
         self,
         list_of_columns: list | str,
-        df: pd.DataFrame | None = None,
+        df: pd.DataFrame,
     ):
         """Alters the dataframe to only hold the given columns.
 
@@ -251,7 +258,6 @@ class DataFile:
         -------
 
         """
-        df = self.df if df is None else df
         # ensure that the input is a list, so that isin() can do its job
         if isinstance(list_of_columns, str):
             list_of_columns = [list_of_columns]

seabirdfilehandler/file_collection.py

@@ -74,7 +74,7 @@ class FileCollection(UserList):
     def collect_files(
         self,
         sorting_key: Callable | None = lambda file: int(
-            file.stem.split("_")[4]
+            file.stem.split("_")[3]
         ),
     ):
         """ """

seabirdfilehandler/geomar_ctd_file_parser.py

@@ -0,0 +1,80 @@
+from pathlib import Path
+import pandas as pd
+
+
+class GEOMARCTDFile:
+    """
+    A parser to read .ctd files created by the GEOMAR processing software.
+
+    Goes through the file line by line and sorts the individual lines in
+    corresponding lists. That way, data and different types of metadata are
+    structured on a basic level.
+    In general, this parser is meant to stick close to the way the Seabird-
+    Parsers are written.
+    """
+
+    def __init__(
+        self,
+        path_to_file: Path | str,
+        only_header: bool = False,
+        create_dataframe: bool = True,
+    ):
+        self.path_to_file = Path(path_to_file)
+        self.only_header = only_header
+        self.raw_input = []
+        self.metadata = {}
+        self.history = []
+        self.comment = []
+        self.data_header = []
+        self.raw_data = []
+        self.read_file()
+        if create_dataframe:
+            self.create_dataframe()
+
+    def __str__(self) -> str:
+        return "/n".join(self.raw_data)
+
+    def __repr__(self) -> str:
+        return str(self.path_to_file.absolute())
+
+    def __eq__(self, other) -> bool:
+        return self.raw_data == other.raw_data
+
+    def read_file(self):
+        with open(self.path_to_file, "r") as file:
+            past_header = False
+            for line in file:
+                self.raw_input.append(line)
+                if line.startswith("History"):
+                    self.history.append(
+                        line.removeprefix("History  = # GEOMAR").strip()
+                    )
+                elif line.startswith("Comment"):
+                    self.comment.append(
+                        line.removeprefix("Comment  =").strip()
+                    )
+                elif line.startswith("Columns"):
+                    self.data_header = [
+                        column.removeprefix("Columns  =").strip()
+                        for column in line.split(":")
+                    ]
+                    past_header = True
+                    if self.only_header:
+                        break
+                else:
+                    if not past_header:
+                        try:
+                            key, value = line.split("=")
+                        except ValueError:
+                            key = line
+                            value = ""
+                        self.metadata[key.strip()] = value.strip()
+                    else:
+                        self.raw_data.append(line)
+
+    def create_dataframe(self):
+        self.df = pd.DataFrame(
+            [row.split() for row in self.raw_data],
+            dtype=float,
+            columns=self.data_header,
+        )

{seabirdfilehandler-0.5.0.dist-info → seabirdfilehandler-0.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: seabirdfilehandler
-Version: 0.5.0
+Version: 0.5.2
 Summary: Library of parsers to interact with SeaBird CTD files.
 Keywords: CTD,parser,seabird,data
 Author: Emil Michels

seabirdfilehandler-0.5.2.dist-info/RECORD

@@ -0,0 +1,15 @@
+seabirdfilehandler/__init__.py,sha256=rS1NfxKVWgOntk5NL-ndZyDt3LHW_tKr_F3iW_QbYvg,230
+seabirdfilehandler/bottlefile.py,sha256=nnfoDczPMG_ge40dT2rHNhifR7-NRgnZNFrfPM_9OSQ,5925
+seabirdfilehandler/bottlelogfile.py,sha256=MtMmEebdAktO3mk6KbmJC7dfx9sRLbV5qqDQt2qtpJE,4310
+seabirdfilehandler/cnvfile.py,sha256=LXpJcC3ukiD-2b5vy4aKESCbIvwV12TwQy1G6Y25_GE,9709
+seabirdfilehandler/datafiles.py,sha256=lqENvdGSwRKT6PyNFN2etaWKMA-4OONG0x-up1W5ezo,8991
+seabirdfilehandler/file_collection.py,sha256=b5iJaP4F34Vq7-FiJOlPvfS4IePGWsYx20XwWbZQw1A,6882
+seabirdfilehandler/geomar_ctd_file_parser.py,sha256=4eCnkE0mvPKC8Dic8sXP4xpfwnk3K2MQcGFBf6loT8k,2655
+seabirdfilehandler/parameter.py,sha256=UuwFzege94sqPt0kOjEqtMGGol4hjuFjj2_EH7o0pzA,14374
+seabirdfilehandler/utils.py,sha256=5KXdB8Hdv65dv5tPyXxNMct1mCEOyA3S8XP54AFAnx0,1745
+seabirdfilehandler/validation_modules.py,sha256=eZ6x0giftUtlxnRMOnK_vCkgccdwUXPrDjajFa-E6n0,4698
+seabirdfilehandler/xmlfiles.py,sha256=L_puQf8eg0ojv85AyEMID4jnwkOlV_fgZP3W5yeSUBY,4668
+seabirdfilehandler-0.5.2.dist-info/LICENSE,sha256=Ifd1VPmYv32oJd2QVh3wIQP9X05vYJlcY6kONz360ws,34603
+seabirdfilehandler-0.5.2.dist-info/METADATA,sha256=ER8rZi5Ei76THx_JdYv7JuXjNjIyErAzS_RMHd-Pspc,1289
+seabirdfilehandler-0.5.2.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+seabirdfilehandler-0.5.2.dist-info/RECORD,,

seabirdfilehandler/dataframe_meta_accessor.py

@@ -1,184 +0,0 @@
-import pandas as pd
-import logging
-from pandas.api.extensions import register_series_accessor
-from pandas.api.extensions import register_dataframe_accessor
-import warnings
-
-
-logger = logging.getLogger(__name__)
-
-
-class MetadataHandler:
-    """
-    The base class for the pandas series and dataframe accessors.
-    Offers a very basic metadata handling, by using a dictionary as metadata
-    store. The accessors then allow to access this metadata store and
-    corresponding methods by calling 'df.meta' or 'series.meta', respectively.
-    Mainly targeted for usage with dataframes featuring data from CNV files,
-    it for example allows the attachement of parameter metadata found in the
-    CNV header to individual dataframe columns.
-
-    This approach was chosen over others, like directly subclassing the pandas
-    dataframe or series class, or a seperate metadata storage, due to its
-    simplicity and ability to keep using the full powerfull pandas library
-    without the need to implement each and every transformation. Of course,
-    the 'attrs' attribute does offer a similar metadata storage. But at the
-    time of writing this, it is still in a very experimental condition and does
-    not propagate reliably.
-    """
-
-    def __init__(self, pandas_obj):
-        self._obj = pandas_obj
-        if not hasattr(self._obj, "_metadata_store"):
-            with warnings.catch_warnings():
-                warnings.simplefilter("ignore")
-                self._obj._metadata_store = {}
-
-    @property
-    def metadata(self):
-        return self._obj._metadata_store
-
-    @metadata.setter
-    def metadata(self, value):
-        self._obj._metadata_store = value
-
-    def get(self, key, default=None):
-        return self._obj._metadata_store.get(key, default)
-
-    def set(self, key, value):
-        self._obj._metadata_store[key] = value
-
-    def clear(self):
-        self._obj._metadata_store.clear()
-
-
-@register_series_accessor("meta")
-class SeriesMetaAccessor(MetadataHandler):
-    """
-    Series implementation of the Metadata Accessor.
-    Does not offer anything more than the base class at the moment.
-    """
-
-    def __init__(self, pandas_obj):
-        super().__init__(pandas_obj)
-
-
-@register_dataframe_accessor("meta")
-class DataFrameMetaAccessor(MetadataHandler):
-    """
-    DataFrame implementation of the Metadata Accessor.
-    Introduces another attribute, '_header_level_detail', that stores the
-    currently displayed metadata as column names. Additionally offers methods
-    to sync metadata between the dataframe and its series, and the handling of
-    common operations, like renaming or the addition of new columns.
-    """
-
-    def __init__(self, pandas_obj):
-        super().__init__(pandas_obj)
-        if not hasattr(self._obj, "_header_level_detail"):
-            self._obj._header_level_detail = "shortname"
-        # Initialize DataFrame metadata
-        self.aggregate_series_metadata()
-
-    @property
-    def header_detail(self):
-        return self._obj._header_level_detail
-
-    @header_detail.setter
-    def header_detail(self, value):
-        self._obj._header_level_detail = value
-
-    @property
-    def metadata(self):
-        return self._obj._metadata_store
-
-    @metadata.setter
-    def metadata(self, value):
-        meta_dict = {
-            shortname: self.add_default_metadata(shortname, metainfo)
-            for shortname, metainfo in value.items()
-        }
-        self._obj._metadata_store = meta_dict
-        self.propagate_metadata_to_series()
-
-    def aggregate_series_metadata(self):
-        """Aggregate metadata from Series within the DataFrame."""
-        for column in self._obj.columns:
-            if isinstance(self._obj[column], pd.Series) and hasattr(
-                self._obj[column], "meta"
-            ):
-                self.metadata[column] = self._obj[column].meta.metadata
-
-    def propagate_metadata_to_series(self):
-        """Propagate DataFrame-level metadata back to Series."""
-        for column in self._obj.columns:
-            if isinstance(self._obj[column], pd.Series) and hasattr(
-                self._obj[column], "meta"
-            ):
-                for key, value in self.metadata.items():
-                    if key == column:
-                        try:
-                            self._obj[column].meta.metadata = value
-                        except TypeError:
-                            logger.error(f"{column}: {value}")
-
-    def update_metadata_on_rename(self, rename_dict):
-        """Update metadata when columns are renamed."""
-        new_metadata = {}
-        for old_name, new_name in rename_dict.items():
-            for key, value in self.metadata.items():
-                if key == old_name:
-                    new_metadata[new_name] = value
-        self.metadata = new_metadata
-        self.propagate_metadata_to_series()
-
-    def rename(self, rename_key):
-        """Rename the column names by using a metadata point."""
-        rename_dict = {
-            column: (
-                self._obj[column].meta.get(rename_key)
-                if rename_key in list(self._obj[column].meta.metadata.keys())
-                else column
-            )
-            for column in self._obj.columns
-        }
-        self._obj.rename(columns=rename_dict, inplace=True)
-        self.header_detail = rename_key
-        self.update_metadata_on_rename(rename_dict)
-
-    def add_column(
-        self,
-        name: str,
-        data: pd.Series | list,
-        location: int | None = None,
-        metadata: dict = {},
-    ):
-        """Add a column and use or generate metadata for it."""
-        location = len(self._obj.columns) if location is None else location
-        self._obj.insert(
-            loc=location,
-            column=name,
-            value=data,
-            allow_duplicates=False,
-        )
-        self.metadata[name] = self.add_default_metadata(name, metadata)
-        self.propagate_metadata_to_series()
-
-    def add_default_metadata(
-        self,
-        name: str,
-        metadata: dict = {},
-        list_of_keys: list = [
-            "shortname",
-            "longinfo",
-            "name",
-            "metainfo",
-            "unit",
-        ],
-    ) -> dict:
-        """Fill up missing metadata points with a default value."""
-        default = {}
-        for key in list_of_keys:
-            if key not in list(metadata.keys()):
-                default[key] = name
-        return {**metadata, **default}

seabirdfilehandler/logging.yaml

@@ -1,23 +0,0 @@
-version: 1
-formatters:
-  simple:
-    format: '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
-handlers:
-  console:
-    class: logging.StreamHandler
-    level: DEBUG
-    formatter: simple
-    stream: ext://sys.stdout
-  file:
-    class: logging.FileHandler
-    filename: seabirdfiles.log
-    level: DEBUG
-    formatter: simple
-loggers:
-  simpleExample:
-    level: DEBUG
-    handlers: [console]
-    propagate: no
-root:
-  level: DEBUG
-  handlers: [console]

seabirdfilehandler-0.5.0.dist-info/RECORD

@@ -1,16 +0,0 @@
-seabirdfilehandler/__init__.py,sha256=5JTzYE3oRdrxkC9_etAnFQ1cy10PHtpmesdR6n5PoPQ,192
-seabirdfilehandler/bottlefile.py,sha256=QBUqtKhD-dUPbgc_sz8NOGEFFkAjL3g5r1oAsqQnUcQ,6063
-seabirdfilehandler/bottlelogfile.py,sha256=CjBeITQS27Ar80bfxguoAnVkYxI1ioAiVTnlvwevw7E,4448
-seabirdfilehandler/cnvfile.py,sha256=-mCuQX76uuWIETljem1DjzDbZ5eNIUucjoHejTQu_sU,9685
-seabirdfilehandler/datafiles.py,sha256=z27PZJBvEbl1aFXpDQ0QTM_yR5NTaNK-HC9_z3t7zuM,8991
-seabirdfilehandler/dataframe_meta_accessor.py,sha256=x4mSEN49us6Ezzjdt41fl5Ry8IJR09ORrZ1roOIJbyc,6439
-seabirdfilehandler/file_collection.py,sha256=qkEdlI-hcoyuOdmgTr8wdAr1mXXkVuKkF9J4j2-v3kY,6882
-seabirdfilehandler/logging.yaml,sha256=mXxbhJPio3OGaukTpc3rLGA8Ywq1DNqp0Vn5YCbH6jY,459
-seabirdfilehandler/parameter.py,sha256=UuwFzege94sqPt0kOjEqtMGGol4hjuFjj2_EH7o0pzA,14374
-seabirdfilehandler/utils.py,sha256=5KXdB8Hdv65dv5tPyXxNMct1mCEOyA3S8XP54AFAnx0,1745
-seabirdfilehandler/validation_modules.py,sha256=eZ6x0giftUtlxnRMOnK_vCkgccdwUXPrDjajFa-E6n0,4698
-seabirdfilehandler/xmlfiles.py,sha256=L_puQf8eg0ojv85AyEMID4jnwkOlV_fgZP3W5yeSUBY,4668
-seabirdfilehandler-0.5.0.dist-info/LICENSE,sha256=Ifd1VPmYv32oJd2QVh3wIQP9X05vYJlcY6kONz360ws,34603
-seabirdfilehandler-0.5.0.dist-info/METADATA,sha256=jPHzHpxz9OY48QHifHT9crI9a5pxYae1aCw6jAhqtYM,1289
-seabirdfilehandler-0.5.0.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-seabirdfilehandler-0.5.0.dist-info/RECORD,,