toolsos 0.2.0__py3-none-any.whl → 0.2.2__py3-none-any.whl

toolsos/{database_connection.py → database/database_connection.py}

@@ -33,7 +33,7 @@ def get_db_connection_strings(
     for dbname, params in db_info.items():
         flush = dbname in reset_pw if reset_pw else False
 
-        if params["pw"] == "acces_token":
+        if params["password"] == "access_token":
             pw = get_azure_access_token()
         else:
             pw = get_pw_from_keyring(dbname=dbname, user=params["user"], reset_pw=flush)
@@ -104,11 +104,13 @@ if __name__ == "__main__":
     # Examples
 
     # Get database connection settings from yaml
-    # engine_strings = get_db_connection_strings("python/database_config.yml")
-    # print(engine_strings.ruimte_analyse222)
+    engine_strings = get_db_connection_strings(
+        "src/toolsos/database/database_config.yml"
+    )
+    print(engine_strings.ruimte_analyse222)
 
     # Get database connection settings from yaml and reset password
-    # engine_strings = get_db_connection_strings(
-    #     "python/database_config.yml", reset_pw=["ruimte_analyse222"]
-    # )
-    # print(engine_strings.ruimte_analyse222)
+    engine_strings = get_db_connection_strings(
+        "src/toolsos/database/database_config.yml", reset_pw=["ruimte_analyse222"]
+    )
+    print(engine_strings.ruimte_analyse222)

toolsos/huisstijl/tables/table_helpers.py

@@ -0,0 +1,76 @@
+from pathlib import Path
+
+import pandas as pd
+import win32com.client as win32
+
+
+def remove_underscores_from_columns(df: pd.DataFrame) -> pd.DataFrame:
+    df.columns = df.columns.str.replace("_", " ")
+    return df
+
+
+def get_excel_files_from_folder(folder: str) -> list[str]:
+    return [str(f.resolve()) for f in Path("to_merge").glob("*") if f.suffix == ".xlsx"]
+
+
+def combine_excel_files(out_path: str, files: list[str] = None, overwrite: bool = True):
+    out_path = Path(out_path)
+
+    if overwrite:
+        if out_path.exists():
+            out_path.unlink()
+
+    # INITIALIZE EXCEL COM APP
+    try:
+        xlapp = win32.gencache.EnsureDispatch("Excel.Application")
+
+        # constants
+        xlPasteValues = -4163
+        lPasteFormats = -4122
+        xlWorkbookDefault = 51
+
+        # create new workbook
+        new_wb = xlapp.Workbooks.Add()
+        new_wb.SaveAs(Filename=str(out_path), FileFormat=xlWorkbookDefault)
+
+        dup_count = 1
+
+        for wb in files:
+            xlwb = xlapp.Workbooks.Open(wb)
+
+            for xlsh in xlwb.Worksheets:
+                new_sh = new_wb.Worksheets.Add()
+
+                try:
+                    new_sh.Name = xlsh.Name
+
+                # Ugly non defined exception. Be aware that this wil caputre
+                except Exception as e:
+                    new_sh.Name = f"{xlsh.Name}_{dup_count}"
+                    dup_count += 1
+
+                new_wb.Save()
+                new_sh.Move(After=new_wb.Worksheets(new_wb.Worksheets.Count))
+
+                xlsh.Cells.Copy(new_sh.Cells)
+                new_sh = None
+
+            xlwb.Close(True)
+            xlwb = None
+
+        # remove default blad1
+        new_wb.Worksheets("Blad1").Delete()
+        new_wb.Save()
+
+    except Exception as e:
+        print(e)
+
+    # RELEASE RESOURCES
+    finally:
+        xlsh = None
+        new_sh = None
+        xlwb = None
+        new_wb = None
+        xlapp.Quit()
+        xlapp = None
+        xlwb = None

toolsos/huisstijl/tables/tables.py

@@ -7,8 +7,7 @@ from typing import Any, Callable, Dict
 import numpy as np
 import pandas as pd
 from openpyxl import Workbook
-from openpyxl.styles import (Alignment, Border, Font, PatternFill, Protection,
-                             Side)
+from openpyxl.styles import Alignment, Border, Font, PatternFill, Protection, Side
 from openpyxl.utils import get_column_letter
 
 Fmt = list[list[dict[str, Any]]]
@@ -47,6 +46,36 @@ def set_global_style(style: str) -> None:
         STYLES = STYLE_NEW
 
 
+def cols_to_str(df: pd.DataFrame) -> pd.DataFrame:
+    """Change column names in to string. Multiindex column names are nog changed because
+    these are always strings
+
+    Args:
+        df (pd.DataFrame): Dataframe
+
+    Returns:
+        pd.DataFrame: Dataframe with column names as strings
+    """
+    if df.columns.nlevels == 1:
+        df.columns = df.columns.astype(str)
+
+    return df
+
+
+def get_max_col_widths(data: pd.DataFrame | np.ndarray) -> list[float]:
+    col_widths = []
+    if isinstance(data, pd.DataFrame):
+        for col in zip(*flatten_multiindex_columns(data)):
+            col_widths.append(max(len(e) for e in col))
+    else:
+        for col in zip(*data):
+            col_widths.append(max(len(str(e)) for e in col))
+
+    col_widths = [col_width * 1.13 for col_width in col_widths]
+
+    return col_widths
+
+
 def flatten_multiindex_columns(df):
     column_multi = []
     for level in range(df.columns.nlevels):
@@ -68,7 +97,18 @@ def df_to_array(df: pd.DataFrame) -> np.ndarray:
     return np.vstack([column_names, df.to_numpy()])
 
 
-def get_cells_to_merge(df: pd.DataFrame) -> list[list[int]]:
+def get_cells_to_merge(df: pd.DataFrame) -> dict[int : list[int, int]]:
+    """Pandas dataframes sometimes have mutliindex columns. For all but the last level
+    a dictionary is created to merge the cells. The last level isn't merged because these
+    are these contain unique column names
+
+    Args:
+        df (pd.DataFrame): Pandas dataframe. If the dataframe has multicolumn indices
+        a dictionary containg the cells to merge is returned
+
+    Returns:
+        dict[int: list[int, int]]: Dictionary containg the cells to merge
+    """
     levels = flatten_multiindex_columns(df)[:-1]
 
     cells_to_merge = {}
@@ -331,14 +371,14 @@ def cell_formatting(
     return fmt
 
 
-def write_worksheet(
+def write_to_worksheet(
     ws: Any,
     arr: np.ndarray,
     fmt: Fmt,
     title: str | None = None,
     source: str | None = None,
     col_filter: bool | None = None,
-    autofit_columns: bool | None = None,
+    col_widths: list | None = None,
     cells_to_merge: list[list[int]] | None = None,
 ) -> None:
     """Writing data to worksheet. Used for writing values to cells and formatting the cells
@@ -379,36 +419,32 @@ def write_worksheet(
         filters = ws.auto_filter
         filters.ref = f"A1:{excel_style(len(fmt), len(fmt[0]))}"
 
-    if autofit_columns:
-        _autofit_columns(ws)
-
     if source:
         _insert_source(ws, source, arr)
 
+    if col_widths:
+        _set_column_widths(ws, col_widths)
+
     if title:
         _insert_title(ws, title)
 
     if cells_to_merge:
-        _merge_cells(ws, cells_to_merge)
+        _merge_cells(ws, cells_to_merge, title)
 
 
-# def _set_column_width(ws: Any, column_widths: list) -> None:
-#     for i, column_number in enumerate(range(ws.max_column)):
-#         column_letter = get_column_letter(column_letter)
-#         column_width = column_widths[i]
-#         ws.column_dimensions[column_letter].width = column_width
+def _set_column_widths(ws: Any, col_widths: list[int]) -> None:
+    for idx, col_width in enumerate(col_widths):
+        col_letter = get_column_letter(idx + 1)
+        ws.column_dimensions[col_letter].width = col_width
 
 
-def _autofit_columns(ws: Any) -> None:
-    column_letters = tuple(
-        get_column_letter(col_number + 1) for col_number in range(ws.max_column)
-    )
-    for column_letter in column_letters:
-        ws.column_dimensions[column_letter].auto_fit = True
-
+def _merge_cells(ws, cells_to_merge, title: str | None = None) -> None:
+    add = 0
+    if title:
+        add = 1
 
-def _merge_cells(ws, cells_to_merge):
     for row_idx, merge in cells_to_merge.items():
+        row_idx = row_idx + add
         for start, stop in merge:
             cell = ws.cell(row_idx + 1, start)
             cell.alignment = Alignment(horizontal="center")
@@ -422,14 +458,15 @@ def _merge_cells(ws, cells_to_merge):
 
 def _insert_source(ws, source, arr):
     height, width = arr.shape
-    cell = ws.cell(width, height + 1, source)
-    cell.font = Font(**STYLES["calibri"]["font"])
+    cell = ws.cell(height + 1, width, source)
     cell.alignment = Alignment(horizontal="right")
+    cell.font = Font(**STYLES["calibri"]["font"])
 
 
 def _insert_title(ws: Any, title: str) -> None:
     ws.insert_rows(0)
     cell = ws.cell(1, 1, title)
+    cell.alignment = Alignment(horizontal="left")
     for t, kwa in STYLES["title_bold"].items():
         setattr(cell, t, LOOKUP[t](**kwa))
 
@@ -455,10 +492,99 @@ def write_table(
     blue_border: bool | None = True,
     blue_border_row_ids: int | list[int] | None = None,
     number_format: str = "0.0",
-    autofit_columns: bool | None = False,
+    autofit_columns: str | None = "column_names",
     col_filter: bool | None = False,
     style: str = "old",
     combine_multiindex: bool | int = False,
+    column_names_to_string: bool = True,
+):
+    wb = Workbook()
+    # Empty sheet is created on Workbook creation
+    del wb["Sheet"]
+
+    set_global_style(style)
+
+    if not isinstance(data, dict):
+        data = {"Sheet1": data}
+
+    for sheet_name, df in data.items():
+        if column_names_to_string == True:
+            df = cols_to_str(df)
+
+        format_worksheet(
+            wb=wb,
+            df=df,
+            sheet_name=sheet_name,
+            header_row=header_row,
+            title=title,
+            source=source,
+            total_row=total_row,
+            light_blue_row_ids=light_blue_row_ids,
+            total_col=total_col,
+            right_align_ids=right_align_ids,
+            right_align_pattern=right_align_pattern,
+            right_align_numeric=right_align_numeric,
+            left_align_ids=left_align_ids,
+            left_align_pattern=left_align_pattern,
+            left_align_string=left_align_string,
+            perc_ids=perc_ids,
+            perc_pattern=perc_pattern,
+            perc_col_format=perc_col_format,
+            blue_border=blue_border,
+            blue_border_row_ids=blue_border_row_ids,
+            number_format=number_format,
+            autofit_columns=autofit_columns,
+            col_filter=col_filter,
+            combine_multiindex=combine_multiindex,
+            column_names_to_string=column_names_to_string,
+        )
+
+    wb.save(file)
+
+
+def write_table_from_dict(
+    file,
+    write_info,
+    style: str = "old",
+):
+    wb = Workbook()
+    # Empty sheet is created on Workbook creation
+    del wb["Sheet"]
+
+    set_global_style(style)
+
+    for sheet in write_info:
+        format_worksheet(wb=wb, **sheet)
+
+    wb.save(file)
+
+
+def format_worksheet(
+    wb: Any,
+    df: pd.DataFrame,
+    sheet_name: str,
+    header_row: int = 0,
+    title: str | dict[str, str] | None = None,
+    source: str | None = None,
+    total_row: bool | None = None,
+    light_blue_row_ids: int | list[int] | None = None,
+    total_col: bool | None = None,
+    right_align_ids: list | None = None,
+    right_align_pattern: str | None = None,
+    right_align_numeric: bool | None = True,
+    left_align_ids: list | None = None,
+    left_align_pattern: str | None = None,
+    left_align_string: bool | None = True,
+    perc_ids: list | None = None,
+    perc_pattern: str | None = None,
+    perc_col_format: str | None = None,
+    blue_border: bool | None = True,
+    blue_border_row_ids: int | list[int] | None = None,
+    number_format: str = "0.0",
+    autofit_columns: str | None = "column_names",
+    col_filter: bool | None = False,
+    combine_multiindex: bool | int = False,
+    column_names_to_string: bool = True,
 ):
     """_summary_
 
@@ -481,107 +607,108 @@ def write_table(
         perc_col_format (str, optional): The formatting string of percentage columns. Defaults to None.
         col_filter (bool, optional): Set filter on columns. Defaults to False.
     """
+    arr = df_to_array(df)
+
+    blue_rows = []
+    light_blue_rows = []
+    light_blue_cols = []
+    blue_border_ids = []
+    r_align_ids = []
+    l_align_ids = []
+    p_ids = []
+    cells_to_merge = []
+    title_tbl = None
+    title_src = None
+
+    if isinstance(header_row, int):
+        blue_rows.extend(list(range(0, header_row + 1)))
 
-    wb = Workbook()
-    # Empty sheet is created on Workbook creation
-    del wb["Sheet"]
-
-    set_global_style(style)
-
-    if not isinstance(data, dict):
-        data = {"Sheet1": data}
-
-    for sheet_name, df in data.items():
-        arr = df_to_array(df)
-
-        blue_rows = []
-        light_blue_rows = []
-        light_blue_cols = []
-        blue_border_ids = []
-        r_align_ids = []
-        l_align_ids = []
-        p_ids = []
-        cells_to_merge = []
-        title_tbl = None
-
-        if isinstance(header_row, int):
-            blue_rows.extend(list(range(0, header_row + 1)))
-
-        if title:
-            if isinstance(title, str):
-                title_tbl = title
-            elif isinstance(title, dict):
-                title_tbl = title.get(sheet_name)
-
-        if right_align_ids:
-            r_align_ids.extend(right_align_ids)
+    if title:
+        if isinstance(title, str):
+            title_tbl = title
+        elif isinstance(title, dict):
+            title_tbl = title.get(sheet_name)
 
-        if right_align_pattern:
-            r_align_ids.extend(get_cols_id_with_pattern(df, right_align_pattern))
+    if source:
+        if isinstance(source, str):
+            title_src = source
+        elif isinstance(title, dict):
+            title_src = source.get(sheet_name)
 
-        if right_align_numeric:
-            r_align_ids.extend(get_numeric_col_ids(df))
+    if right_align_ids:
+        r_align_ids.extend(right_align_ids)
 
-        if left_align_ids:
-            r_align_ids.extend(left_align_ids)
+    if right_align_pattern:
+        r_align_ids.extend(get_cols_id_with_pattern(df, right_align_pattern))
 
-        if left_align_pattern:
-            l_align_ids.extend(get_cols_id_with_pattern(df, left_align_pattern))
+    if right_align_numeric:
+        r_align_ids.extend(get_numeric_col_ids(df))
 
-        if left_align_string:
-            l_align_ids.extend(get_string_cols_ids(df))
+    if left_align_ids:
+        r_align_ids.extend(left_align_ids)
 
-        if perc_ids:
-            p_ids.extend(perc_ids)
+    if left_align_pattern:
+        l_align_ids.extend(get_cols_id_with_pattern(df, left_align_pattern))
 
-        if perc_pattern:
-            r_id = get_cols_id_with_pattern(df, perc_pattern)
-            p_ids.extend(r_id)
-            r_align_ids.extend(r_id)
+    if left_align_string:
+        l_align_ids.extend(get_string_cols_ids(df))
 
-        if total_row:
-            light_blue_rows.append(arr.shape[0] - 1)
+    if perc_ids:
+        p_ids.extend(perc_ids)
 
-        if light_blue_row_ids:
-            light_blue_rows.extend(light_blue_row_ids)
+    if perc_pattern:
+        r_id = get_cols_id_with_pattern(df, perc_pattern)
+        p_ids.extend(r_id)
+        r_align_ids.extend(r_id)
 
-        if total_col:
-            light_blue_cols.append(arr.shape[1] - 1)
+    if total_row:
+        light_blue_rows.append(arr.shape[0] - 1)
 
-        if blue_border:
-            blue_border_ids.append(arr.shape[0] - 1)
+    if light_blue_row_ids:
+        light_blue_rows.extend(light_blue_row_ids)
 
-        if blue_border_row_ids:
-            blue_border_ids.extend(blue_border_row_ids)
+    if total_col:
+        light_blue_cols.append(arr.shape[1] - 1)
 
-        if combine_multiindex:
-            cells_to_merge = get_cells_to_merge(df)
+    if blue_border:
+        blue_border_ids.append(arr.shape[0] - 1)
 
-        ws = wb.create_sheet(sheet_name)
+    if blue_border_row_ids:
+        blue_border_ids.extend(blue_border_row_ids)
 
-        fmt = cell_formatting(
-            arr=arr,
-            default_format=STYLES["calibri"],
-            blue_row_ids=blue_rows,
-            light_blue_row_ids=light_blue_rows,
-            light_blue_col_ids=light_blue_cols,
-            left_align_ids=l_align_ids,
-            right_align_ids=r_align_ids,
-            perc_col_ids=p_ids,
-            perc_col_format=perc_col_format,
-            number_format=number_format,
-            blue_border_ids=blue_border_ids,
-        )
+    if combine_multiindex:
+        cells_to_merge = get_cells_to_merge(df)
 
-        write_worksheet(
-            ws=ws,
-            arr=arr,
-            fmt=fmt,
-            title=title_tbl,
-            source=source,
-            col_filter=col_filter,
-            autofit_columns=autofit_columns,
-            cells_to_merge=cells_to_merge,
-        )
+    if autofit_columns == "column_names":
+        col_widths = get_max_col_widths(df)
+    elif autofit_columns == "all_data":
+        col_widths = get_max_col_widths(arr)
+    else:
+        col_widths = None
+
+    ws = wb.create_sheet(sheet_name)
+
+    fmt = cell_formatting(
+        arr=arr,
+        default_format=STYLES["calibri"],
+        blue_row_ids=blue_rows,
+        light_blue_row_ids=light_blue_rows,
+        light_blue_col_ids=light_blue_cols,
+        left_align_ids=l_align_ids,
+        right_align_ids=r_align_ids,
+        perc_col_ids=p_ids,
+        perc_col_format=perc_col_format,
+        number_format=number_format,
+        blue_border_ids=blue_border_ids,
+    )
 
-    wb.save(file)
+    write_to_worksheet(
+        ws=ws,
+        arr=arr,
+        fmt=fmt,
+        title=title_tbl,
+        source=title_src,
+        col_filter=col_filter,
+        col_widths=col_widths,
+        cells_to_merge=cells_to_merge,
+    )

{toolsos-0.2.0.dist-info → toolsos-0.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: toolsos
-Version: 0.2.0
+Version: 0.2.2
 Summary: OS tools
 Author-email: OS <d.schmitz@amsterdam.nl>
 Keywords: tools,Onderzoek & Statistiek

{toolsos-0.2.0.dist-info → toolsos-0.2.2.dist-info}/RECORD

@@ -1,12 +1,12 @@
 toolsos/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 toolsos/cbs_tools.py,sha256=VLhptzy7m5EaET07s6VeAfDz79g1Hs38qeWPyA14wkw,2823
 toolsos/create_tables.py,sha256=43FHK3EERjumBtnGhngIdtthZzcc_Qi37lJ1MgATzBg,908
-toolsos/database_connection.py,sha256=BlHzLS17KzJP_7R5-IBd8WqgwAt-zDRwJXD4Jx6Tetw,3323
-toolsos/database_transfer.py,sha256=1ghq5VEtKyOdCKdM45uOyrZSoXMuWsdC35R3WNuFvdU,1827
 toolsos/download.py,sha256=88hehmPL5m5d1nrcJjltuh4xrCItF5EYHaZdHOcSt-g,2652
 toolsos/geo.py,sha256=_OexkeUgXcnPW1mw27VN6fMcX2PMUSljLwIg48Xkv3M,2412
 toolsos/helpers.py,sha256=VeOl-fLgePCbjEmAQdVmYe7z8OE1pISeDDuP1t5QSxM,997
 toolsos/polars_helpers.py,sha256=P3RHLQFeDL7-9U_Q1n4ma_NSkdYAiker4pnc57uluHw,770
+toolsos/database/database_connection.py,sha256=z5uDDfw3GPAjWp4rVLwNaE2xpW8n_pgfrZ7cf1D-Mks,3362
+toolsos/database/database_transfer.py,sha256=1ghq5VEtKyOdCKdM45uOyrZSoXMuWsdC35R3WNuFvdU,1827
 toolsos/huisstijl/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 toolsos/huisstijl/colors.py,sha256=lSCHCdSjge5cGfLfAObd6mV6TaXq3QGImLOmoGJpGkw,1484
 toolsos/huisstijl/graphs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -16,9 +16,10 @@ toolsos/huisstijl/graphs/linegraph.py,sha256=xTYgBwY_aaWnOL9Oz9Ogzhis9OIkEhDSIBk
 toolsos/huisstijl/graphs/piegraph.py,sha256=Pzc3vrbvlkv40V3OYWh6bDDc5arRRwJq7dfRzplPKWY,571
 toolsos/huisstijl/graphs/styler.py,sha256=XmPLX8sRxcH2OFWn49hzZ6IhAlmCHjUC_m9LKE9c3Sw,6626
 toolsos/huisstijl/tables/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+toolsos/huisstijl/tables/table_helpers.py,sha256=jsQ6lw93sxtGJGrUn8X2_LyA2vYYnytngpUI5A_wpWQ,2037
 toolsos/huisstijl/tables/table_styles.py,sha256=oYU6GJcfqlKpZof5PUjPsA7woJ3Tew78CHPyT0_jY6w,1343
-toolsos/huisstijl/tables/tables.py,sha256=geu-udWBbVFKk5CArhaTqJvoWPSmQ4-sC66CBkUWZug,19779
-toolsos-0.2.0.dist-info/METADATA,sha256=4AFPTjCSnQYcNRk7-m4ZgP40NIwl-Dv9SZbNb0iv0v8,2433
-toolsos-0.2.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-toolsos-0.2.0.dist-info/top_level.txt,sha256=2ClEjUBbtfDQ8oPwvWRy1Sz2nrkLCXlg0mHaMdCWia0,8
-toolsos-0.2.0.dist-info/RECORD,,
+toolsos/huisstijl/tables/tables.py,sha256=GDoo526nXq61tWM86KFaPy67ZmCza9GhkkksW_ATtM4,23575
+toolsos-0.2.2.dist-info/METADATA,sha256=-3UieU8bcMm51-B6N1wdf8atHpOZFCdjakc7D1hp4Bk,2433
+toolsos-0.2.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+toolsos-0.2.2.dist-info/top_level.txt,sha256=2ClEjUBbtfDQ8oPwvWRy1Sz2nrkLCXlg0mHaMdCWia0,8
+toolsos-0.2.2.dist-info/RECORD,,