PyDPEET 0.2.0__py3-none-any.whl

pydpeet/io/device/arbin_4_23_PV090331/reader.py

@@ -0,0 +1,68 @@
+import pandas as pd
+
+from pydpeet.io.configs.const import PANDAS_EXCEL_ENGINE
+
+
+def to_dataframe(input_path: str) -> tuple[pd.DataFrame, str]:
+    """
+    Parses the input file from the Arbin Old Cycler into a pandas DataFrame.
+
+    Parameters:
+    input_path (str): Path to the input file.
+
+    Returns:
+    (pandas.DataFrame, str): A tuple containing the DataFrame with data and metadata as a string.
+    """
+    # load Excel data
+    excel_data = pd.ExcelFile(input_path, engine=PANDAS_EXCEL_ENGINE)
+
+    return read_sheets(excel_data)
+
+
+def read_sheets(excel_file: pd.ExcelFile) -> tuple[pd.DataFrame, str]:
+    # variables for the dataframe and String
+    """
+    Reads data from all sheets in an Excel file and returns them as a tuple of a DataFrame and a string.
+
+    The first sheet that starts with "Channel" is used as the main data sheet. If there are more sheets with this name,
+    they are appended to the first sheet.
+
+    All sheets named "Info" are concatenated into a single string as metadata.
+
+    Parameters:
+    excel_file (pd.ExcelFile): The Excel file to read from.
+
+    Returns:
+    (pd.DataFrame, str): A tuple containing the DataFrame with data and metadata as a string.
+    """
+    arbin_df = None
+    metadata_str = []
+    iterator = 0
+
+    # iterate all sheets
+    for sheet_name in excel_file.sheet_names:
+        # find sheet that starts with "Channel"
+        if sheet_name.startswith("Channel"):
+            # if it´s the first sheet, that starts with the channel, it gets added to df
+            if iterator == 0:
+                arbin_df = excel_file.parse(sheet_name, header=0)
+            # if it´s the second or higher Sheet, it will be appended without the header and the first row,
+            # because first row of 2nd sheet and last row of first sheet are the same
+            else:
+                # get Data from further Sheet(s)
+                # remove the first two rows (header and multiple row)
+                further_sheet_data = excel_file.parse(sheet_name, header=0).iloc[1:]
+                # concat both sheets into one
+                arbin_df = pd.concat([arbin_df, further_sheet_data], ignore_index=True)
+            iterator += 1
+        # combine all other sheets into a string as metadata
+        elif sheet_name.startswith("Info"):
+            # only metadata sheet in arbin Old is called "Info"
+            sheet_data = excel_file.parse(sheet_name, header=None)  # no header
+            sheet_str = f"Sheet: {sheet_name}\n{sheet_data.to_string(index=False, header=False)}"
+            metadata_str.append(sheet_str)
+
+    # combine all metadata sheets into one string
+    metadata_str_combined = "\n\n".join(metadata_str)
+
+    return arbin_df, metadata_str_combined

pydpeet/io/device/arbin_8_00_PV221201/__init__.py

@@ -0,0 +1,7 @@
+"""
+Auto-generated __init__ file.
+Created: 2026-03-06 15:11:49
+"""
+
+# Restrictive package init: start with no public API
+__all__ = []

pydpeet/io/device/arbin_8_00_PV221201/formatter.py

@@ -0,0 +1,26 @@
+import pandas as pd
+
+from pydpeet.io.utils.formatter_utils import (
+    absolute_time_timedate_typecast,
+    testtime_hours_to_seconds_with_string_interpretation,
+)
+
+
+def get_data_into_format(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Format the given DataFrame into a standard format.
+
+    Parameters
+    ----------
+    data_frame : pandas.DataFrame
+        The DataFrame to be formatted
+
+    Returns
+    -------
+    pandas.DataFrame
+        The formatted DataFrame
+    """
+    df = testtime_hours_to_seconds_with_string_interpretation(df, True)
+    df = absolute_time_timedate_typecast(df)
+
+    return df

pydpeet/io/device/arbin_8_00_PV221201/mapper.py

@@ -0,0 +1,18 @@
+# Map raw-data column names (left) to standardized column names (right)
+COLUMN_MAP = {
+    "Record number": "Step_Count",
+    "Voltage(V)": "Voltage[V]",
+    "Current(A)": "Current[A]",
+    "Relative Time(h:min:s.ms)": "Test_Time[s]",
+    "Real Time(h:min:s.ms)": "Date_Time",
+}
+
+# Default columns of the standardized format
+# which are not present in the raw data files.
+MISSING_REQUIRED_COLUMNS = [
+    "Temperature[°C]",
+    "EIS_f[Hz]",
+    "EIS_Z_Real[Ohm]",
+    "EIS_Z_Imag[Ohm]",
+    "EIS_DC[A]",
+]

pydpeet/io/device/arbin_8_00_PV221201/reader.py

@@ -0,0 +1,66 @@
+import pandas as pd
+
+from pydpeet.io.configs.const import PANDAS_EXCEL_ENGINE
+
+
+def to_dataframe(input_path: str) -> tuple[pd.DataFrame, str]:
+    """
+    Parses the input file from the Arbin Cycler into a pandas DataFrame.
+
+    Parameters:
+    input_path (str): Path to the input file.
+
+    Returns:
+    (pandas.DataFrame, str): A tuple containing the DataFrame with data and metadata as a string.
+    """
+    # load Excel data
+    excel_data = pd.ExcelFile(input_path, engine=PANDAS_EXCEL_ENGINE)
+
+    return read_sheets(excel_data)
+
+
+def read_sheets(excel_file: pd.ExcelFile) -> tuple[pd.DataFrame, str]:
+    """
+    Reads data from all sheets in an Excel file and returns them as a tuple of a DataFrame and a string.
+
+    The first sheet that starts with "Detail" is used as the main data sheet. If there are more sheets with this name,
+    they are appended to the first sheet.
+
+    All other sheets are concatenated into a single string as metadata.
+
+    Parameters:
+    excel_file (pd.ExcelFile): The Excel file to read from.
+
+    Returns:
+    (pd.DataFrame, str): A tuple containing the DataFrame with data and metadata as a string.
+    """
+    # variables for the dataframe and String
+    arbin_df = None
+    metadata_str = []
+    iterator = 0
+
+    # iterate all sheets
+    for sheet_name in excel_file.sheet_names:
+        # find sheet that starts with "Detail"
+        if sheet_name.startswith("Detail"):
+            # if it´s the first sheet, that starts with the channel, it gets added to df
+            if iterator == 0:
+                arbin_df = excel_file.parse(sheet_name, header=0)
+            # if it´s the second or higher Sheet, it will be appended without the header and the first row,
+            # because first row of 2nd sheet and last row of first sheet are the same
+            else:
+                # get Data from further Sheet(s)
+                # remove the first two rows (header and multiple row)
+                further_sheet_data = excel_file.parse(sheet_name, header=0).iloc[1:]
+                # concat bot sheets into one
+                arbin_df = pd.concat([arbin_df, further_sheet_data])
+            iterator += 1
+        else:  # combine all other sheets into a string as metadata
+            sheet_data = excel_file.parse(sheet_name, header=None)  # no header
+            sheet_str = f"Sheet: {sheet_name}\n{sheet_data.to_string(index=False, header=False)}"
+            metadata_str.append(sheet_str)
+
+    # combine all metadata sheets into one string
+    metadata_str_combined = "\n\n".join(metadata_str)
+
+    return arbin_df, metadata_str_combined

pydpeet/io/device/basytec_6_3_1_0/__init__.py

@@ -0,0 +1,7 @@
+"""
+Auto-generated __init__ file.
+Created: 2026-03-06 15:11:49
+"""
+
+# Restrictive package init: start with no public API
+__all__ = []

pydpeet/io/device/basytec_6_3_1_0/formatter.py

@@ -0,0 +1,18 @@
+import pandas as pd
+
+from pydpeet.io.utils.formatter_utils import round_testtime, testtime_hours_to_seconds_direct
+
+
+def get_data_into_format(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Takes a pandas DataFrame and applies two functions to it:
+
+    1. `testtime_hours_to_seconds_direct`: converts the "Test_Time[s]" column from hours to seconds with string interpretation.
+    2. `round_testtime`: rounds the "Test_Time[s]" column down to the nearest second.
+
+    Returns the modified DataFrame.
+    """
+    df = testtime_hours_to_seconds_direct(df)
+    df = round_testtime(df)
+
+    return df

pydpeet/io/device/basytec_6_3_1_0/mapper.py

@@ -0,0 +1,18 @@
+# Map raw-data column names (left) to standardized column names (right)
+COLUMN_MAP = {
+    "Time[h]": "Test_Time[s]",
+    "U[V]": "Voltage[V]",
+    "I[A]": "Current[A]",
+    "T1[°C]": "Temperature[°C]",
+    "Line": "Step_Count",
+}
+
+# Default columns of the standardized format
+# which are not present in the raw data files.
+MISSING_REQUIRED_COLUMNS = [
+    "Date_Time",
+    "EIS_f[Hz]",
+    "EIS_Z_Real[Ohm]",
+    "EIS_Z_Imag[Ohm]",
+    "EIS_DC[A]",
+]

pydpeet/io/device/basytec_6_3_1_0/reader.py

@@ -0,0 +1,54 @@
+import logging
+from io import StringIO
+
+import pandas as pd
+
+
+def to_dataframe(input_path: str) -> tuple[pd.DataFrame, str]:
+    """
+    Parses the input file from the basytec cycler into a pandas DataFrame.
+    It first converts the data portion to CSV format in memory.
+
+    Parameters:
+        input_path (str): Path to the input file.
+
+    Returns:
+        (pd.DataFrame, str): A tuple containing the DataFrame with the data and metadata as a string.
+    """
+    with open(input_path, encoding="iso-8859-1") as file:
+        lines = file.readlines()
+
+    # Collect all metadata lines (those starting with '~')
+    metadata_lines = []
+    data_start_idx = 0
+    for idx, line in enumerate(lines):
+        if line.startswith("~"):
+            metadata_lines.append(line.strip())
+        else:
+            data_start_idx = idx
+            break
+
+    if not metadata_lines:
+        logging.warning("The file does not contain expected metadata lines starting with '~'.")
+
+    # The last metadata line is used as the header; remove it from metadata_lines.
+    header_line = metadata_lines.pop().lstrip("~").strip()
+    headers = header_line.split()
+
+    # Join the remaining metadata lines into a single string.
+    metadata_str = "\n".join(metadata_lines)
+
+    # Convert the remaining data lines into CSV format.
+    csv_lines = [",".join(headers)]  # CSV header
+    for line in lines[data_start_idx:]:
+        line = line.strip()
+        if line:  # Skip empty lines.
+            # Split on whitespace then join with commas.
+            csv_lines.append(",".join(line.split()))
+
+    csv_content = "\n".join(csv_lines)
+
+    # Use StringIO to read the CSV content into a DataFrame.
+    df = pd.read_csv(StringIO(csv_content))
+
+    return df, metadata_str

pydpeet/io/device/digatron_4_20_6_236/__init__.py

@@ -0,0 +1,7 @@
+"""
+Auto-generated __init__ file.
+Created: 2026-03-06 15:11:49
+"""
+
+# Restrictive package init: start with no public API
+__all__ = []

pydpeet/io/device/digatron_4_20_6_236/formatter.py

@@ -0,0 +1,27 @@
+import pandas as pd
+
+from pydpeet.io.utils.formatter_utils import absolute_time_timedate_typecast, fix_time_format
+
+
+def get_data_into_format(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Applies a series of transformations to the input DataFrame to
+    ensure that the "Date_Time" column is in the correct
+    datetime format. The time format is initially fixed using the specified
+    input format, and then typecast to pandas datetime objects.
+
+    Parameters
+    ----------
+    data_frame : pd.DataFrame
+        The DataFrame to be formatted.
+
+    Returns
+    -------
+    pd.DataFrame
+        The formatted DataFrame with the "Date_Time"
+        column converted to datetime objects.
+    """
+    fix_time_format(df, input_format="%d.%m.%Y %H:%M:%S")
+    absolute_time_timedate_typecast(df)
+
+    return df

pydpeet/io/device/digatron_4_20_6_236/mapper.py

@@ -0,0 +1,18 @@
+# Map raw-data column names (left) to standardized column names (right)
+COLUMN_MAP = {
+    "Schritt Zeit": "Test_Time[s]",
+    "Spannung": "Voltage[V]",
+    "Strom": "Current[A]",
+    "Schritt Nr.": "Step_Count",
+    "Zeitstempel": "Date_Time",
+    "T_Batt": "Temperature[°C]",
+}
+
+# Default columns of the standardized format
+# which are not present in the raw data files.
+MISSING_REQUIRED_COLUMNS = [
+    "EIS_f[Hz]",
+    "EIS_Z_Real[Ohm]",
+    "EIS_Z_Imag[Ohm]",
+    "EIS_DC[A]",
+]

pydpeet/io/device/digatron_4_20_6_236/reader.py

@@ -0,0 +1,45 @@
+import pandas as pd
+
+
+def to_dataframe(input_path: str) -> tuple[pd.DataFrame, str]:
+    """
+    Parses the input file from the Digatron Cycler into a pandas DataFrame.
+
+    Parameters:
+    input_path (str): Path to the input file.
+
+    Returns:
+    (pandas.DataFrame, str): A tuple containing the DataFrame with data and metadata as a string.
+    """
+    metadata = []
+
+    # Open the file and process lines
+    with open(input_path, encoding="us-ascii") as file:
+        # Read metadata until the header line is found
+        line = file.readline()
+        while not line.startswith("Zeitstempel"):
+            metadata.append(line.strip())
+            line = file.readline()
+
+        # Extract headers and remaining data
+        headers = line.strip().split(";")
+        data_lines = [row.strip().split(";") for row in file if row.strip()]
+
+        # appending first string from datalines
+        metadata.append(";".join(data_lines.pop(0)))
+
+    # Join metadata into a single string
+    metadata_str = "\n".join(metadata)
+
+    # Create DataFrame
+    df = pd.DataFrame(data_lines, columns=headers)
+
+    # Convert numeric columns to appropriate types
+    for col in headers:
+        try:
+            df[col] = pd.to_numeric(df[col])
+        except ValueError:
+            # Leave non-numeric columns as is
+            pass
+
+    return df, metadata_str

pydpeet/io/device/digatron_eis_4_20_6_236/__init__.py

@@ -0,0 +1,7 @@
+"""
+Auto-generated __init__ file.
+Created: 2026-03-06 15:11:49
+"""
+
+# Restrictive package init: start with no public API
+__all__ = []

pydpeet/io/device/digatron_eis_4_20_6_236/formatter.py

@@ -0,0 +1,39 @@
+import pandas as pd
+
+from pydpeet.io.utils.formatter_utils import (
+    absolute_time_timedate_typecast,
+    apply_convert_to_float_if_possible,
+    move_strings_from_column_to_metadata,
+    nan_to_none_in_column,
+    replace_empty_with_none_in_standard_columns,
+    round_testtime,
+    typecast,
+)
+
+
+def get_data_into_format(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Format the given DataFrame into a standard format.
+
+    Parameters
+    ----------
+    data_frame : pandas.DataFrame
+        The DataFrame to be formatted
+
+    Returns
+    -------
+    pandas.DataFrame
+        The formatted DataFrame
+    """
+    df = replace_empty_with_none_in_standard_columns(df)
+    typecast(df, "Step_Count", int)
+    df = apply_convert_to_float_if_possible(df, "Voltage[V]")
+    df = apply_convert_to_float_if_possible(df, "Current[A]")
+    df = round_testtime(df)
+    df = absolute_time_timedate_typecast(df)
+    typecast(df, "EIS_Z_Real[Ohm]", float)
+    typecast(df, "EIS_Z_Imag[Ohm]", float)
+    df = nan_to_none_in_column(df, "Current[A]")
+    df = move_strings_from_column_to_metadata(df, "Voltage[V]")
+
+    return df

pydpeet/io/device/digatron_eis_4_20_6_236/mapper.py

@@ -0,0 +1,18 @@
+# Map raw-data column names (left) to standardized column names (right)
+COLUMN_MAP = {
+    "Zreal1": "EIS_Z_Real[Ohm]",
+    "Zimg1": "EIS_Z_Imag[Ohm]",
+    "Zeitstempel": "Date_Time",
+    "Schritt Nr.": "Step_Count",
+    "Spannung": "Voltage[V]",
+    "Strom": "Current[A]",
+    "Progr. Zeit": "Test_Time[s]",
+}
+
+# Default columns of the standardized format
+# which are not present in the raw data files.
+MISSING_REQUIRED_COLUMNS = [
+    "Temperature[°C]",
+    "EIS_f[Hz]",
+    "EIS_DC[A]",
+]

pydpeet/io/device/digatron_eis_4_20_6_236/reader.py

@@ -0,0 +1,42 @@
+import pandas as pd
+
+
+def to_dataframe(input_path: str) -> tuple[pd.DataFrame, str]:
+    """
+    Parses the input file from the Digatron Cycler into a pandas DataFrame.
+
+    Parameters:
+    input_path (str): Path to the input file.
+
+    Returns:
+    (pandas.DataFrame, str): A tuple containing the DataFrame with data and metadata as a string.
+    """
+    metadata = []
+
+    # Open the file and process lines
+    with open(input_path, encoding="iso-8859-1") as file:
+        # Read metadata until the header line is found
+        line = file.readline()
+        while not line.startswith("Zeitstempel"):
+            metadata.append(line.strip())
+            line = file.readline()
+
+        # Extract headers and remaining data
+        headers = line.strip().split(",")
+        # TODO: Why is this still here?
+        # for i in range(4):
+        #    line = file.readline()
+        #    metadata.append(line.strip())
+
+        data_lines = [row.strip().split(",") for row in file if row.strip()]
+
+        # appending first string from datalines
+        metadata.append(";".join(data_lines.pop(0)))
+
+    # Join metadata into a single string
+    metadata_str = "\n".join(metadata)
+
+    # Create DataFrame
+    df = pd.DataFrame(data_lines, columns=headers)
+
+    return df, metadata_str

pydpeet/io/device/neware_8_0_0_516/__init__.py

@@ -0,0 +1,7 @@
+"""
+Auto-generated __init__ file.
+Created: 2026-03-06 15:11:49
+"""
+
+# Restrictive package init: start with no public API
+__all__ = []

pydpeet/io/device/neware_8_0_0_516/formatter.py

@@ -0,0 +1,31 @@
+import pandas as pd
+
+from pydpeet.io.utils.formatter_utils import (
+    absolute_time_timedate_typecast,
+    testtime_hours_to_seconds_with_string_interpretation,
+    typecast,
+)
+
+
+def get_data_into_format(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Format a DataFrame from a Neware cycler into a standard format.
+
+    The DataFrame is modified in-place.
+
+    Parameters
+    ----------
+    data_frame : pd.DataFrame
+        DataFrame to be formatted
+
+    Returns
+    -------
+    pd.DataFrame
+        Formatted DataFrame
+    """
+    testtime_hours_to_seconds_with_string_interpretation(df, True)
+    df = absolute_time_timedate_typecast(df)
+    typecast(df, "Step_Count", int)
+    typecast(df, "Temperature[°C]", float)
+
+    return df

pydpeet/io/device/neware_8_0_0_516/mapper.py

@@ -0,0 +1,18 @@
+# Map raw-data column names (left) to standardized column names (right)
+COLUMN_MAP = {
+    "step_id": "Step_Count",
+    "Voltage(V)": "Voltage[V]",
+    "Current[A] - record": "Current[A]",
+    "T1": "Temperature[°C]",
+    "Total Time": "Test_Time[s]",
+    "Date": "Date_Time",
+}
+
+# Default columns of the standardized format
+# which are not present in the raw data files.
+MISSING_REQUIRED_COLUMNS = [
+    "EIS_f[Hz]",
+    "EIS_Z_Real[Ohm]",
+    "EIS_Z_Imag[Ohm]",
+    "EIS_DC[A]",
+]