clean up maccor

cellpy/readers/core.py

@@ -14,7 +14,7 @@
 import sys
 import time
 import warnings
-from typing import Any, Tuple, Dict, List, Union, TypeVar
+from typing import Any, Tuple, Dict, List, Union, TypeVar, Optional
 
 import numpy as np
 import pandas as pd
@@ -711,9 +711,16 @@ def generate_default_factory():
 
 
 # TODO: v1.1.0 - implement plugins and local instrument readers
-def find_all_instruments() -> Dict[str, Tuple[str, pathlib.Path]]:
+def find_all_instruments(
+    name_contains: Optional[str] = None,
+) -> Dict[str, Tuple[str, pathlib.Path]]:
     """finds all the supported instruments"""
 
+    if name_contains:
+        glob_txt = f"*{name_contains}*.py"
+    else:
+        glob_txt = "*.py"
+
     import cellpy.readers.instruments as hard_coded_instruments_site
 
     instruments_found = {}
@@ -724,7 +731,7 @@ def find_all_instruments() -> Dict[str, Tuple[str, pathlib.Path]]:
     ).parent
     modules_in_hard_coded_instruments_site = [
         s
-        for s in hard_coded_instruments_site.glob("*.py")
+        for s in hard_coded_instruments_site.glob(glob_txt)
         if not (
             str(s.name).startswith("_")
             or str(s.name).startswith("dev_")

cellpy/readers/instruments/base.py

@@ -670,12 +670,23 @@ class TxtLoader(AutoLoader, ABC):
     raw_ext = "*"
 
     # override this if needed
-    def parse_loader_parameters(self, **kwargs):
-        sep = kwargs.get("sep", None)
-        if sep is not None:
-            self.sep = sep
-        if self.sep is None:
+    def parse_loader_parameters(self, auto_formatter=None, **kwargs):
+        """Parse the loader parameters.
+
+        Args:
+            auto_formatter: if True, the formatter will be set to auto-formatting.
+            **kwargs: keyword arguments.
+        """
+
+        if auto_formatter:
             self._auto_formatter()
+        else:
+            # backup option - do auto-formatting if sep is not given
+            sep = kwargs.get("sep", None)
+            if sep is not None:
+                self.sep = sep
+            if self.sep is None:
+                self._auto_formatter()
 
     # override this if needed
     def parse_formatter_parameters(self, **kwargs):
@@ -715,6 +726,7 @@ def parse_formatter_parameters(self, **kwargs):
         )
 
     def _auto_formatter(self):
+        print("auto-formatting")
         separator, first_index = find_delimiter_and_start(
             self.name,
             separators=None,

cellpy/readers/instruments/configurations/maccor_txt_one.py

@@ -1,4 +1,8 @@
-# not updated yet
+"""Configuration for tab-delimited Maccor txt files with three comment rows (used by UBham in the SIMBA project)."""
+
+# currently skips the comment rows instead of parsing them (change this by modifying the formatters
+# and add preprocessing step for parsing them)
+
 unit_labels = {
     "resistance": "Ohms",
     # not observed yet:

cellpy/readers/instruments/configurations/maccor_txt_three.py

@@ -1,82 +1,77 @@
-# Works for data from WMG and UBham (SIMBA project)
+"""Configuration for tab-delimited Maccor txt files with two comment rows (used by WMG in the SIMBA project)."""
+
+# currently skips the comment rows instead of parsing them (change this by modifying the formatters
+# and add preprocessing step for parsing them)
+
+file_info = {"raw_extension": "txt"}
 
 unit_labels = {
     "resistance": "Ohms",
     "time": "s",
-    "current": "Amps",
-    "voltage": "Volts",
-    "power": "Watt-hr",
-    "capacity": "Amp-hr",
+    "current": "A",
+    "voltage": "V",
+    "power": "W",
+    "capacity": "Ah",
     "energy": "Wh",
     "temperature": "C",
 }
 
-prefixes = {
-    "G": 1000_000_000,
-    "M": 1000_000,
-    "k": 1000.0,
-    "h": 100.0,
-    "d": 10.0,
-    "c": 0.01,
-    "m": 0.001,
-    "micro": 0.000_001,
-    "n": 0.000_000_001,
-}
-
 normal_headers_renaming_dict = {
-    "data_point_txt": f"Rec#",
-    "datetime_txt": f"DPt Time",
-    "test_time_txt": f"TestTime",
-    "step_time_txt": f"StepTime",
-    "cycle_index_txt": f"Cyc#",
-    "step_index_txt": f"Step",
+    "data_point_txt": "Rec#",
+    "cycle_index_txt": "Cyc#",
+    "step_index_txt": "Step",
+    "test_time_txt": "TestTime",
+    "step_time_txt": "StepTime",
+    "charge_capacity_txt": "mAmp-hr",
+    "charge_energy_txt": "mWatt-hr",
+    "current_txt": "mAmps",
+    "voltage_txt": "Volts",
+    "datetime_txt": "DPt Time",
 }
 
-file_info = {"raw_extension": "txt"}
-
 states = {
     "column_name": "State",
     "charge_keys": ["C"],
     "discharge_keys": ["D"],
     "rest_keys": ["R"],
 }
 
+
 raw_units = {"current": "A", "charge": "Ah", "mass": "g", "voltage": "V"}
 
-# raw_limits = {
-#     "current_hard": 0.000_000_000_000_1,
-#     "current_soft": 0.000_01,
-#     "stable_current_hard": 2.0,
-#     "stable_current_soft": 4.0,
-#     "stable_voltage_hard": 2.0,
-#     "stable_voltage_soft": 4.0,
-#     "stable_charge_hard": 0.001,
-#     "stable_charge_soft": 5.0,
-#     "ir_change": 0.00001,
-# }
+raw_limits = {
+    "current_hard": 0.000_000_000_000_1,
+    "current_soft": 0.000_01,
+    "stable_current_hard": 2.0,
+    "stable_current_soft": 4.0,
+    "stable_voltage_hard": 2.0,
+    "stable_voltage_soft": 4.0,
+    "stable_charge_hard": 0.001,
+    "stable_charge_soft": 5.0,
+    "ir_change": 0.00001,
+}
 
 formatters = {
-    "skiprows": 3,  # 12 for other file
+    "skiprows": 2,
     "sep": "\t",
-    "header": 0,  # 0 for other file
+    "header": 0,
     "encoding": "ISO-8859-1",  # options: "ISO-8859-1", "utf-8", "cp1252"
-    "decimal": ".",
-    "thousands": ",",
+    "decimal": ",",
+    "thousands": None,
 }
 
-pre_processors = {}
+pre_processors = {
+    "remove_empty_lines": True,
+}
 
 post_processors = {
-    "get_column_names": True,
     "split_capacity": True,
-    "split_current": False,
+    "split_current": True,
     "set_index": True,
     "rename_headers": True,
-    "remove_last_if_bad": True,
     "set_cycle_number_not_zero": True,
+    "remove_last_if_bad": True,
     "convert_date_time_to_datetime": True,
     "convert_step_time_to_timedelta": True,
     "convert_test_time_to_timedelta": True,
-    "convert_units": True,
-    "select_columns_to_keep": True,
 }

cellpy/readers/instruments/configurations/maccor_txt_two.py

@@ -1,4 +1,7 @@
-# Works for data from KIT (SIMBA project) with ',' as decimal and dropping bad last rows.
+"""Configuration for tab-delimited Maccor txt files with 12 comment rows (used by KIT in the SIMBA project)."""
+
+# currently skips the comment rows instead of parsing them (change this by modifying the formatters
+# and add preprocessing step for parsing them)
 
 unit_labels = {
     "resistance": "Ohms",

cellpy/readers/instruments/maccor_txt.py

@@ -14,18 +14,13 @@
 
 
 SUPPORTED_MODELS = {
-    "ZERO": "maccor_txt_zero",
+    "ZERO": "maccor_txt_zero",  # needs to be updated (does no postprocessing at the moment)
     "ONE": "maccor_txt_one",
     "TWO": "maccor_txt_two",
     "THREE": "maccor_txt_three",
-    "FOUR": "maccor_txt_four",
-    "WMG_SIMBA": "maccor_txt_three",
-    "KIT_SIMBA": "maccor_txt_four",
-    "KIT_COMMA_SIMBA": "maccor_txt_two",
-    "UBHAM_SIMBA": "maccor_txt_three",
-    "S4000-WMG": "maccor_txt_four",
-    "S4000-KIT": "maccor_txt_four",
-    "S4000-UBHAM": "maccor_txt_three",
+    "S4000-UBHAM": "maccor_txt_one",
+    "S4000-KIT": "maccor_txt_two",
+    "S4000-WMG": "maccor_txt_three",
 }
 
 
@@ -424,7 +419,74 @@ def _check_loader_from_outside_with_get2():
     c.save(outfile)
 
 
+def _fix_bugs_now():
+    import pathlib
+
+    import cellpy
+    import pandas as pd
+    import matplotlib.pyplot as plt
+
+    DATADIR = r"C:\scripting\cellpy_dev_resources\dev_data\simba_Maccor\S4000"
+    FILENAME = "01_UBham_CD_M50_Validation_0deg_01.txt"
+    INSTRUMENT = "maccor_txt"
+    MODEL = "ONE"
+
+    pd.options.display.max_columns = 100
+    datadir = pathlib.Path(DATADIR)
+    name = datadir / FILENAME
+    out = pathlib.Path(r"C:\scripting\trash")
+    print(f"File exists? {name.is_file()}")
+    if not name.is_file():
+        print(f"could not find {name} ")
+        return
+
+    c = cellpy.get(
+        filename=name,
+        instrument=INSTRUMENT,
+        model=MODEL,
+        mass=1.0,
+        auto_summary=False,
+        # auto_formatter=True,  # does not work for UBHAM (finds only two comment rows, but should be three)
+        # post_processors={"another_param": False},  # This parameter will be available in the post-processors
+    )
+    print(f"loaded the file - now lets see what we got")
+    raw = c.data.raw
+    raw.to_clipboard()
+    print(raw.head())
+    c.make_step_table()
+    steps = c.data.steps
+    summary = c.data.summary
+
+    raw.to_csv(out / "raw.csv", sep=";")
+    steps.to_csv(out / "steps.csv", sep=";")
+    summary.to_csv(out / "summary.csv", sep=";")
+
+    fig_1, (ax1, ax2, ax3, ax4) = plt.subplots(
+        4,
+        1,
+        figsize=(6, 10),
+        constrained_layout=True,
+        sharex=True,
+    )
+    raw.plot(x="test_time", y="voltage", ax=ax1, xlabel="")
+    raw.plot(x="test_time", y="current", ax=ax2, xlabel="")
+    raw.plot(
+        x="test_time", y=["charge_capacity", "discharge_capacity"], ax=ax3, xlabel=""
+    )
+    raw.plot(x="test_time", y="cycle_index", ax=ax4)
+    fig_1.suptitle(f"{name.name}", fontsize=16)
+
+    n = c.get_number_of_cycles()
+    print(f"Number of cycles: {n}")
+
+    plt.legend()
+    plt.show()
+
+    outfile = out / "test_out"
+    c.save(outfile)
+
+
 if __name__ == "__main__":
     # check_dev_loader2(model="two")
     # check_loader(number=2, model="two")
-    _check_loader_from_outside_with_get()
+    _fix_bugs_now()