tidy

countess/core/plugins.py

@@ -21,13 +21,22 @@
 import os.path
 import sys
 from collections.abc import Mapping, MutableMapping
-from typing import Any, Iterable, Optional, Union, Dict
+from typing import Any, Dict, Iterable, Optional, Union
 
-import pandas as pd
 import numpy as np
+import pandas as pd
 
 from countess.core.logger import Logger
-from countess.core.parameters import ArrayParam, BaseParam, ColumnChoiceParam, FileArrayParam, FileParam, FileSaveParam, MultiParam, StringParam
+from countess.core.parameters import (
+    ArrayParam,
+    BaseParam,
+    ColumnChoiceParam,
+    FileArrayParam,
+    FileParam,
+    FileSaveParam,
+    MultiParam,
+    StringParam,
+)
 from countess.utils.pandas import get_all_columns
 
 PRERUN_ROW_LIMIT = 100000
@@ -167,7 +176,7 @@ def process_inputs(
 class PandasSimplePlugin(PandasBasePlugin):
     """Base class for plugins which accept and return pandas DataFrames"""
 
-    input_columns : Dict[str, np.dtype] = {}
+    input_columns: Dict[str, np.dtype] = {}
 
     def process_inputs(
         self, inputs: Mapping[str, Iterable[pd.DataFrame]], logger: Logger, row_limit: Optional[int]
@@ -207,7 +216,6 @@ def dataframe_to_series(self, dataframe: pd.DataFrame, logger: Logger) -> pd.Ser
         return NotImplementedError(f"{self.__class__}.dataframe_to_series()")
 
     def process_dataframe(self, dataframe: pd.DataFrame, logger: Logger) -> pd.DataFrame:
-
         series = self.dataframe_to_series(dataframe, logger)
         df2 = self.series_to_dataframe(series)
         df3 = dataframe.merge(df2, left_index=True, right_index=True)
@@ -234,7 +242,7 @@ def dataframe_to_series(self, dataframe: pd.DataFrame, logger: Logger) -> pd.Ser
         if column_name in dataframe:
             return dataframe[column_name].apply(self.process_value, logger=logger)
         else:
-            null_values = [ self.process_value(None, logger) ] * len(dataframe)
+            null_values = [self.process_value(None, logger)] * len(dataframe)
             s = pd.Series(null_values, index=dataframe.index)
             return s
 

countess/gui/config.py

@@ -443,7 +443,7 @@ def __init__(self, tk_parent: tk.Widget, plugin: BasePlugin, change_callback=Non
 
     def change_parameter(self, parameter):
         """Called whenever a parameter gets changed"""
-        #if self.plugin.update():
+        # if self.plugin.update():
         #    self.update()
         if self.change_callback:
             self.change_callback(self)

countess/gui/main.py

@@ -91,7 +91,7 @@ def show_config_subframe(self):
         self.config_canvas.grid(row=3, column=0, sticky=tk.NSEW)
         self.config_scrollbar.grid(row=3, column=1, sticky=tk.NS)
 
-        #self.node.prepare(self.logger)
+        # self.node.prepare(self.logger)
 
         if self.node.plugin:
             if self.node.notes:
@@ -113,8 +113,8 @@ def show_config_subframe(self):
                 tk.Button(self.frame, text=UNICODE_INFO, fg="blue", command=self.on_info_button_press).place(
                     anchor=tk.NE, relx=1, y=50
                 )
-            #self.node.prepare(self.logger)
-            #self.node.plugin.update()
+            # self.node.prepare(self.logger)
+            # self.node.plugin.update()
             self.configurator = PluginConfigurator(self.config_canvas, self.node.plugin, self.config_change_callback)
             self.config_subframe = self.configurator.frame
         else:
@@ -148,7 +148,6 @@ def show_notes_widget(self, notes=""):
     def show_preview_subframe(self):
         if self.preview_subframe:
             self.preview_subframe.destroy()
-        print(f"show_preview_subframe {self.node.result}")
         try:
             df = concat_dataframes(self.node.result)
             self.preview_subframe = TabularDataFrame(self.frame)
@@ -158,8 +157,8 @@ def show_preview_subframe(self):
             self.preview_subframe.columnconfigure(0, weight=1)
             tk.Label(self.preview_subframe, text="no result").grid(sticky=tk.EW)
 
-        #if isinstance(self.node.result, pd.DataFrame):
-        #elif isinstance(self.node.result, str):
+        # if isinstance(self.node.result, pd.DataFrame):
+        # elif isinstance(self.node.result, str):
         #    self.preview_subframe = tk.Frame(self.frame)
         #    self.preview_subframe.rowconfigure(1, weight=1)
         #    n_lines = len(self.node.result.splitlines())
@@ -168,7 +167,7 @@ def show_preview_subframe(self):
         #    text.insert("1.0", self.node.result)
         #    text["state"] = "disabled"
         #    text.grid(sticky=tk.NSEW)
-        #else:
+        # else:
 
         self.preview_subframe.grid(row=4, columnspan=2, sticky=tk.NSEW)
 

countess/plugins/csv.py

@@ -20,7 +20,6 @@
 # data types to each column
 
 
-
 def maybe_number(x):
     """CSV is never clear on if something is actually a number so ... try it I guess ..."""
     try:
@@ -133,6 +132,7 @@ def read_file_to_dataframe(self, file_params, logger, row_limit=None):
             for n, col in enumerate(df.columns):
                 if not self.parameters["columns"][n]["name"].value:
                     self.parameters["columns"][n]["name"].value = str(col)
+                    self.parameters["columns"][n]["type"].value = "string"
 
         filename_column = self.parameters["filename_column"].value
         if filename_column:

countess/plugins/data_table.py

@@ -1,4 +1,4 @@
-from typing import Any, Optional, Mapping, Iterable
+from typing import Any, Iterable, Mapping, Optional
 
 import pandas as pd
 

countess/plugins/join.py

@@ -17,6 +17,7 @@ def _join_how(left_required: bool, right_required: bool) -> str:
     else:
         return "right" if right_required else "outer"
 
+
 class JoinPlugin(PandasBasePlugin):
     """Joins Pandas Dataframes"""
 
@@ -51,7 +52,7 @@ def join_dataframes(self, dataframe1: pd.DataFrame, dataframe2: pd.DataFrame, jo
         join2 = join_params.get("right_on")
         if join2 and join2 not in dataframe2.columns and dataframe2.index.name != join2:
             dataframe2 = dataframe2.reset_index()
-        
+
         return dataframe1.merge(dataframe2, **join_params)
 
     def process_inputs(

countess/plugins/regex.py

@@ -51,7 +51,7 @@ def process_dataframe(self, dataframe: pd.DataFrame, logger: Logger) -> pd.DataF
         df = super().process_dataframe(dataframe, logger)
 
         if self.parameters["drop_unmatch"].value:
-            output_names = [ pp.name.value for pp in self.parameters["output"] ]
+            output_names = [pp.name.value for pp in self.parameters["output"]]
             df = df.dropna(subset=output_names, how="all")
 
         if self.parameters["drop_column"].value:

pyproject.toml

@@ -98,6 +98,7 @@ disable = [
     "too-many-instance-attributes",
     "too-many-locals",
     "too-many-statements",
+    "too-few-public-methods",
     "too-many-public-methods",
     "unidiomatic-typecheck",
 ]