toolsos 0.1.4__py3-none-any.whl → 0.2.6__py3-none-any.whl

toolsos/cbs_tools.py

@@ -2,8 +2,9 @@ from __future__ import annotations
 
 import json
 import pickle
+from datetime import datetime
 from pathlib import Path
-from typing import TYPE_CHECKING, Iterator, Optional, Any
+from typing import TYPE_CHECKING, Any, Iterator, Optional
 
 import pandas as pd
 import pyarrow as pa
@@ -14,18 +15,27 @@ if TYPE_CHECKING:
     import pyreadstat
 
 
+def get_batch_size(path, memory_limit):
+    df, _ = prs.read_sav(path, row_limit=1000)
+
+    # memory in megabytes
+    mem_size = df.memory_usage().sum() / 1_000_000
+
+    # The amount of blocks (of a thousand rows fit in the memory_limit)
+    n_blocks = memory_limit / mem_size
+
+    # Calculate the number of rows that fit within the memory limit
+    return round(n_blocks * 1000)
+
+
 class SavToParquet:
     def __init__(
-        self,
-        file: str,
-        folder_out: str,
-        chunksize: Optional[int] = None,
-        verbose: bool = False,
+        self, file: str, folder_out: str, verbose: bool = False, memory_limit=10_000
     ) -> None:
         self.file = file
         self.folder_out = folder_out
         self.verbose = verbose
-        self.chunksize = 5_000_000 if not chunksize else chunksize
+        self.memory_limit = memory_limit
 
     @property
     def path_out(self) -> str:
@@ -33,20 +43,27 @@ class SavToParquet:
 
     @property
     def chunks(self) -> Iterator[tuple["pyreadstat.metadata_container", pd.DataFrame]]:
-        return prs.read_file_in_chunks(
-            prs.read_sav, self.file, chunksize=self.chunksize
-        )
 
-    def get_meta(self) -> Iterator:
-        return prs.read_sav(self.file, row_limit=10)
+        chunksize = get_batch_size(self.file, self.memory_limit)
+
+        if self.verbose:
+            print(f"Reading file in blocks of {chunksize} rows")
+            print("One such block should fit within the memory limit")
+
+        return prs.read_file_in_chunks(prs.read_sav, self.file, chunksize=chunksize)
 
     def write_meta_to_json(self) -> None:
         json_path = self.path_out.replace(".parquet", "_meta.json")
 
         meta_dict = {}
-        for attr in dir(self.meta):
-            if not attr.startswith("__"):
-                meta_dict[attr] = getattr(self.meta, attr)
+        for attr_name in dir(self.meta):
+            if not attr_name.startswith("__"):
+                attr = getattr(self.meta, attr_name)
+
+                if isinstance(attr, datetime):
+                    attr = attr.strftime("%Y-%m-%d %H:%M:%S")
+
+                meta_dict[attr_name] = attr
 
         with open(json_path, "w") as file:
             json.dump(meta_dict, file)
@@ -58,10 +75,12 @@ class SavToParquet:
             pickle.dump(self.meta, file)
 
     def write_to_parquet(self) -> None:
-        meta_df, self.meta = self.get_meta()
-        schema = table = pa.Table.from_pandas(meta_df).schema
 
         print("Writing table")
+
+        line1, self.meta = prs.read_sav(self.file, row_limit=1)
+        schema = pa.Table.from_pandas(line1).schema
+
         with pq.ParquetWriter(self.path_out, schema) as writer:
             for idx, (df, _) in enumerate(self.chunks):
                 if self.verbose:

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

@@ -2,8 +2,10 @@ from __future__ import annotations
 
 import getpass
 import json
+import os
 import subprocess
 from json import JSONDecodeError
+from pathlib import Path
 from typing import Optional
 
 import keyring
@@ -33,7 +35,7 @@ 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)
@@ -94,21 +96,60 @@ def get_azure_access_token():
     result = subprocess.run(command, capture_output=True, shell=True, text=True)
 
     try:
-        json.loads(result.stdout)["accessToken"]
+        return json.loads(result.stdout)["accessToken"]
     except JSONDecodeError:
         subprocess.run("az login", shell=True)
 
 
-if __name__ == "__main__":
-    ...
-    # Examples
+def get_token_from_pgpass() -> None:
+    p = Path(os.getenv("APPDATA")) / "postgresql" / "pgpass.conf"
+    with open(p) as f:
+        token = f.readline().split(":")[4]
 
-    # Get database connection settings from yaml
-    # engine_strings = get_db_connection_strings("python/database_config.yml")
-    # print(engine_strings.ruimte_analyse222)
+    return token
 
-    # 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)
+
+def write_pgpass(
+    host: str, port: str, database: str, user: str, path: str | None = None
+) -> None:
+    password = get_azure_access_token()
+    conn_string = f"{host}:{port}:{database}:{user}:{password}"
+
+    if not path:
+        if os.name == "nt":
+            path = Path(os.getenv("APPDATA")) / "postgresql" / "pgpass.conf"
+        else:
+            path = Path("$home/.pgpass")
+
+    if not path.parent.exists():
+        path.parent.mkdir()
+
+    with open(path, "w") as f:
+        f.write(conn_string)
+
+    if os.name != "nt":
+        path.chmod("0600")
+
+
+def write_multiple_pgpass(conn_details, path: str | None = None):
+    password = get_azure_access_token()
+
+    conn_strings = []
+    for c in conn_details:
+        c_string = f'{c["host"]}:{c["port"]}:{c["database"]}:{c["user"]}:{password}'
+        conn_strings.append(c_string)
+
+    if not path:
+        if os.name == "nt":
+            path = Path(os.getenv("APPDATA")) / "postgresql" / "pgpass.conf"
+        else:
+            path = Path("$home/.pgpass")
+
+    if not path.parent.exists():
+        path.parent.mkdir()
+
+    with open(path, "w") as f:
+        f.writelines(line + "\n" for line in conn_strings)
+
+    if os.name != "nt":
+        path.chmod("0600")

toolsos/geo.py

@@ -17,7 +17,7 @@ def get_geo_json(
     Returns:
         dict[str, str]: geo json containg of the desired level and year
     """
-    base_url = "https://gitlab.com/os-amsterdam/datavisualisatie-onderzoek-en-statistiek/-/raw/main/geo/"
+    base_url = "https://gitlab.com/os-amsterdam/datavisualisatie-onderzoek-en-statistiek/-/raw/main/public/geo/"
 
     if mra:
         level = f"{level}-mra"

toolsos/huisstijl/graphs/bargraph.py

@@ -1,4 +1,5 @@
 import plotly.express as px
+
 from .styler import BaseStyle
 
 basestyle = BaseStyle()
@@ -14,6 +15,7 @@ def bar(
     barmode=None,
     width=750,
     height=490,
+    font="Amsterdam Sans",
     **kwargs,
 ):
     fig = px.bar(
@@ -21,7 +23,7 @@ def bar(
         x=x,
         y=y,
         color=color,
-        template=basestyle.get_base_template("bar", orientation=orientation),
+        template=basestyle.get_base_template("bar", orientation=orientation, font=font),
         width=width,
         color_discrete_sequence=color_discrete_sequence,
         height=height,
@@ -43,6 +45,7 @@ def stacked_single(
     color: str = None,
     color_discrete_sequence: list = None,
     orientation="v",
+    font="Amsterdam Sans",
     **kwargs,
 ):
     fig = bar(
@@ -53,6 +56,7 @@ def stacked_single(
         color_discrete_sequence=color_discrete_sequence,
         barmode="relative",
         orientation=orientation,
+        font=font,
         **kwargs,
     )
 
@@ -71,6 +75,7 @@ def stacked_multiple(
     color: str = None,
     color_discrete_sequence: list = None,
     orientation="v",
+    font="Amsterdam Sans",
     **kwargs,
 ):
     fig = bar(
@@ -81,6 +86,7 @@ def stacked_multiple(
         color_discrete_sequence=color_discrete_sequence,
         barmode="stack",
         orientation=orientation,
+        font=font,
         **kwargs,
     )
 
@@ -94,6 +100,7 @@ def grouped(
     color: str = None,
     color_discrete_sequence: list = None,
     orientation="v",
+    font="Amsterdam Sans",
     **kwargs,
 ):
     fig = bar(
@@ -104,6 +111,7 @@ def grouped(
         color_discrete_sequence=color_discrete_sequence,
         barmode="group",
         orientation=orientation,
+        font=font,
         **kwargs,
     )
 
@@ -116,6 +124,7 @@ def single(
     y: str,
     color_discrete_sequence: list = None,
     orientation="v",
+    font="Amsterdam Sans",
     **kwargs,
 ):
     fig = bar(
@@ -124,6 +133,7 @@ def single(
         y=y,
         color_discrete_sequence=color_discrete_sequence,
         orientation=orientation,
+        font=font,
         **kwargs,
     )
 

toolsos/huisstijl/graphs/graph_styles.py

@@ -1,5 +1,8 @@
+font = "Amsterdam Sans ExtraBold, Corbel"
+# font = "Arial"
+
 STYLE_OLD = {
-    "font": {"family": "Corbel", "font_size": 15},
+    "font": {"family": "Corbel", "size": 15},
     "plot_bgcolor": "#FFFFFF",
     "gridline_color": "#E8E8E8",
     "gridlinewidth": 0.75,
@@ -12,13 +15,18 @@ STYLE_OLD = {
 
 
 STYLE_NEW = {
-    "font": "Amsterdam Sans ExtraBold, Corbel",
-    "font_size": 15,
+    "font_bold": {"family": "Amsterdam Sans ExtraBold, Corbel", "size": 15},
+    "font_bold_corbel": {"family": "Corbel Bold", "size": 15},
+    "font": {"family": "Amsterdam Sans, Corbel", "size": 15},
+    "font_corbel": {"family": "Corbel", "size": 15},
+    "axis_font": {"family": "Amsterdam Sans ExtraBold, Corbel", "size": 15},
     "plot_bgcolor": "#FFFFFF",
-    "gridline_color": "#E8E8E8",
-    "gridlinewidth": 0.75,
+    "gridline_color": "#dbdbdb",
+    "gridline_width": 0.75,
     "showline": True,
     "showgrid": False,
-    "zerolinecolor": "#E8E8E8",
-    "gridcolor": "#E8E8E8",
+    "zerolinecolor": "#dbdbdb",
+    "gridcolor": "#dbdbdb",
+    "gridlinecolor": "#dbdbdb",
+    "separators": ",",
 }

toolsos/huisstijl/graphs/linegraph.py

@@ -1,11 +1,21 @@
 import plotly.express as px
-from .styler import BaseStyle
 
+from .styler import BaseStyle
 
 basestyle = BaseStyle()
 
 
-def line(data, x, y, color: None, width=750, height=490, **kwargs):
+def line(
+    data,
+    x,
+    y,
+    color: None,
+    width=750,
+    height=490,
+    color_discrete_sequence=None,
+    font="Amsterdam Sans",
+    **kwargs,
+):
     fig = px.line(
         data_frame=data,
         x=x,
@@ -13,8 +23,13 @@ def line(data, x, y, color: None, width=750, height=490, **kwargs):
         color=color,
         width=width,
         height=height,
-        template=BaseStyle().get_base_template(graph_type="line"),
+        color_discrete_sequence=color_discrete_sequence,
+        template=BaseStyle().get_base_template(graph_type="line", font=font),
         **kwargs,
     )
 
+    fig.update_layout(
+        dict(xaxis_title_text="", yaxis_title_text="", legend_title_text="")
+    )
+
     return fig

toolsos/huisstijl/graphs/piegraph.py

@@ -1,4 +1,5 @@
 import plotly.express as px
+
 from .styler import BaseStyle
 
 basestyle = BaseStyle()
@@ -12,6 +13,8 @@ def pie(
     width=750,
     height=490,
     text_format: str = None,
+    color_discrete_sequence=None,
+    font="Amsterdam Sans",
     **kwargs,
 ):
     fig = px.pie(
@@ -21,7 +24,8 @@ def pie(
         width=width,
         height=height,
         hole=hole,
-        template=BaseStyle().get_base_template(),
+        template=BaseStyle().get_base_template(font=font),
+        color_discrete_sequence=color_discrete_sequence,
         **kwargs,
     )
 

toolsos/huisstijl/graphs/styler.py

@@ -4,56 +4,153 @@ import plotly.graph_objects as go
 import requests
 from requests import ConnectionError
 
+from .graph_styles import STYLE_NEW
+
+# class BaseStyle:
+#     style_url = (
+#         "https://raw.githubusercontent.com/jbosga-ams/oistyle/main/base_style.json"
+#     )
+
+#     def __init__(self):
+#         self.grab_styling()
+
+#     def grab_styling(self, style_path: str = None):
+#         if not style_path:
+#             try:
+#                 res = requests.get(self.style_url).json()
+#             except ConnectionError:
+#                 print("Failed grabbing basestyle from the interwebs")
+#                 # Add option to manually provide json file
+#         else:
+#             res = json.loads()
+
+#         for k, v in res.items():
+#             setattr(self, k, v)
+
+#         self.font = "Amsterdam Sans ExtraBold, Corbel"
+
+#     def _get_axis_format(self):
+#         self.gridline_color = "#dbdbdb"  # Jorren vragen om deze aan te passen
+
+#         return {
+#             "zerolinecolor": self.gridline_color,
+#             "gridcolor": self.gridline_color,
+#             "gridwidth": self.gridline_width,
+#             "showline": True,
+#             "linewidth": self.gridline_width,
+#             "linecolor": self.gridline_color,
+#             #             "mirror": True,
+#             "showgrid": False,
+#         }
+
+#     def _get_base_template_layout(self):
+#         return go.layout.Template(
+#             layout={
+#                 "font": {"family": self.font, "size": self.font_size},
+#                 "plot_bgcolor": self.plot_bgcolor,
+#                 "colorway": self.colors["darkblue_lightblue_gradient_5"],
+#                 "separators": ",",  # Jorren vragen om deze toe te voegen
+#             }
+#         )
+
+#     def get_base_template(
+#         self, graph_type: str = None, orientation: str = None, colors: str = None
+#     ):
+#         """[summary]
+
+#         Args:
+#             graph_type (str, optional): Pick 'bar', 'line' or 'bar'. Defaults to None.
+#             orientation (str, optional): [description]. Pick horizontal ('h') or vertical 'v'. Defaults to None.
+#             colors (str, optional): Set basecolors. Defaults to None.
+
+#         Raises:
+#             ValueError: [description]
+
+#         Returns:
+#             [type]: [description]
+#         """
+#         base_template = self._get_base_template_layout()
+#         axis_format = self._get_axis_format()
+
+#         if graph_type == "bar":
+#             if orientation in ["v", "vertical"]:
+#                 base_template.layout.xaxis.update(axis_format)
+#                 base_template.layout.yaxis.update(zeroline=False)
+#             elif orientation in ["h", "horizontal"]:
+#                 base_template.layout.yaxis.update(axis_format)
+#                 base_template.layout.xaxis.update(zeroline=False)
+#             else:
+#                 raise ValueError(
+#                     "Orientation ('v'/'vertical' or 'h'/'horizontal') should be supplied with graph_type=='bar'"
+#                 )
+
+#         elif graph_type == "line":
+#             base_template.layout.xaxis.update(axis_format)
+
+#         if colors:
+#             base_template.layout.update({"colorway": colors})
+
+#         return base_template
+
+#     def get_ois_colors(self, colorscale):
+#         colorscale = self.colors.get(colorscale, [])
+#         if not colorscale:
+#             raise Exception(f"Kies uit {self.colors.keys()}")
+
+#         return colorscale
+
 
 class BaseStyle:
-    style_url = (
-        "https://raw.githubusercontent.com/jbosga-ams/oistyle/main/base_style.json"
-    )
-
-    def __init__(self):
-        self.grab_styling()
-
-    def grab_styling(self, style_path: str = None):
-        if not style_path:
-            try:
-                res = requests.get(self.style_url).json()
-            except ConnectionError:
-                print("Failed grabbing basestyle from the interwebs")
-                # Add option to manually provide json file
+    def __init__(self, style_path=None):
+        if style_path is None:
+            self.style = STYLE_NEW
         else:
-            res = json.loads()
-
-        for k, v in res.items():
-            setattr(self, k, v)
-
-        self.font = "Amsterdam Sans ExtraBold, Corbel"
+            with open(style_path) as file:
+                self.style = json.load(file)
 
     def _get_axis_format(self):
-        self.gridline_color = "#dbdbdb"  # Jorren vragen om deze aan te passen
 
         return {
-            "zerolinecolor": self.gridline_color,
-            "gridcolor": self.gridline_color,
-            "gridwidth": self.gridline_width,
+            "zerolinecolor": self.style["gridline_color"],
+            "gridcolor": self.style["gridline_color"],
+            "gridwidth": self.style["gridline_width"],
             "showline": True,
-            "linewidth": self.gridline_width,
-            "linecolor": self.gridline_color,
-            #             "mirror": True,
-            "showgrid": False,
+            "linewidth": self.style["gridline_width"],
+            "linecolor": self.style["gridline_color"],
+            "showgrid": self.style["showgrid"],
         }
 
-    def _get_base_template_layout(self):
+    def _get_base_template_layout(self, font):
+        if font == "Amsterdam Sans":
+            font_ = self.style["font"]
+            font_bold_ = self.style["font_bold"]
+        elif font == "Corbel":
+            font_ = self.style["font_corbel"]
+            font_bold_ = self.style["font_bold_corbel"]
+        else:
+            raise ValueError("Font should be 'Amsterdam Sans' or 'Corbel'")
+
         return go.layout.Template(
             layout={
-                "font": {"family": self.font, "size": self.font_size},
-                "plot_bgcolor": self.plot_bgcolor,
-                "colorway": self.colors["darkblue_lightblue_gradient_5"],
-                "separators": ",",  # Jorren vragen om deze toe te voegen
+                "xaxis": {
+                    "tickfont": font_bold_,
+                },
+                "yaxis": {
+                    "tickfont": font_bold_,
+                },
+                "legend": {"font": font_},
+                "plot_bgcolor": self.style["plot_bgcolor"],
+                "separators": ",",
+                "font": font_bold_,
             }
         )
 
     def get_base_template(
-        self, graph_type: str = None, orientation: str = None, colors: str = None
+        self,
+        graph_type: str = None,
+        orientation: str = None,
+        colors: str = None,
+        font: str = "Amsterdam Sans",
     ):
         """[summary]
 
@@ -68,7 +165,7 @@ class BaseStyle:
         Returns:
             [type]: [description]
         """
-        base_template = self._get_base_template_layout()
+        base_template = self._get_base_template_layout(font)
         axis_format = self._get_axis_format()
 
         if graph_type == "bar":
@@ -90,14 +187,3 @@ class BaseStyle:
             base_template.layout.update({"colorway": colors})
 
         return base_template
-
-    def get_ois_colors(self, colorscale):
-        colorscale = self.colors.get(colorscale, [])
-        if not colorscale:
-            raise Exception(f"Kies uit {self.colors.keys()}")
-
-        return colorscale
-
-
-class Basestyle2:
-    def __init__(self, style): ...

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

@@ -46,6 +46,38 @@ 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
+    """
+
+    # Multiindex columns are always strings and therefore can't be casted as string
+    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):
@@ -67,20 +99,32 @@ def df_to_array(df: pd.DataFrame) -> np.ndarray:
     return np.vstack([column_names, df.to_numpy()])
 
 
-def get_cells_to_merge(df, n_levels=1):
-    levels = flatten_multiindex_columns(df)
-    levels = levels[0:n_levels]
+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
 
-    merge_cells = []
-    start_col = 1
+    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]
 
-    for level in levels:
+    cells_to_merge = {}
+    for level_idx, level in enumerate(levels):
+        start_col = 1
+        start_col = 1
+        merge_cells = []
         for _, val in groupby(level):
             val = list(val)
             merge_cells.append([start_col, start_col + len(val) - 1])
             start_col += len(val)
+        cells_to_merge[level_idx] = merge_cells
 
-    return merge_cells
+    return cells_to_merge
 
 
 def get_fmt_table(arr: np.ndarray) -> Fmt:
@@ -329,14 +373,15 @@ 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,
+    min_column_width: int | 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
@@ -377,51 +422,61 @@ 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, min_column_width)
+
     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], min_column_width: int | None
+) -> None:
+    for idx, col_width in enumerate(col_widths):
+        col_letter = get_column_letter(idx + 1)
 
+        if min_column_width:
+            if col_width < min_column_width:
+                col_width = min_column_width
+
+        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 start, stop in cells_to_merge:
-        cell = ws.cell(1, start)
-        cell.alignment = Alignment(horizontal="left")
-        ws.merge_cells(start_row=1, end_row=1, start_column=start, end_column=stop)
+    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")
+            ws.merge_cells(
+                start_row=row_idx + 1,
+                end_row=row_idx + 1,
+                start_column=start,
+                end_column=stop,
+            )
 
 
 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))
 
@@ -447,10 +502,99 @@ 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",
+    min_column_width: int | None = None,
     col_filter: bool | None = False,
     style: str = "old",
-    combine_multiindex_cols: bool | int = False,
+    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():
+        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,
+            min_column_width=min_column_width,
+            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",
+    min_column_width: int | None = None,
+    col_filter: bool | None = False,
+    combine_multiindex: bool | int = False,
+    column_names_to_string: bool = True,
 ):
     """_summary_
 
@@ -473,107 +617,112 @@ 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.
     """
+    if column_names_to_string == True:
+        df = cols_to_str(df)
 
-    wb = Workbook()
-    # Empty sheet is created on Workbook creation
-    del wb["Sheet"]
-
-    set_global_style(style)
+    arr = df_to_array(df)
 
-    if not isinstance(data, dict):
-        data = {"Sheet1": data}
+    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
 
-    for sheet_name, df in data.items():
-        arr = df_to_array(df)
+    if isinstance(header_row, int):
+        blue_rows.extend(list(range(0, header_row + 1)))
 
-        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_cols:
-            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,
+        min_column_width=min_column_width,
+    )

{toolsos-0.1.4.dist-info → toolsos-0.2.6.dist-info}/METADATA

@@ -1,31 +1,31 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: toolsos
-Version: 0.1.4
+Version: 0.2.6
 Summary: OS tools
 Author-email: OS <d.schmitz@amsterdam.nl>
 Keywords: tools,Onderzoek & Statistiek
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
-Requires-Python: >=3.11
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
-Provides-Extra: all
-Requires-Dist: keyring ; extra == 'all'
-Requires-Dist: openpyxl ; extra == 'all'
-Requires-Dist: pandas ; extra == 'all'
-Requires-Dist: plotly ; extra == 'all'
-Requires-Dist: polars ; extra == 'all'
-Requires-Dist: pyarrow ; extra == 'all'
-Requires-Dist: pyreadstat ; extra == 'all'
-Requires-Dist: pyyaml ; extra == 'all'
-Requires-Dist: requests ; extra == 'all'
-Requires-Dist: sqlalchemy ; extra == 'all'
 Provides-Extra: dev
-Requires-Dist: black ; extra == 'dev'
-Requires-Dist: bumpver ; extra == 'dev'
-Requires-Dist: isort ; extra == 'dev'
-Requires-Dist: pip-tools ; extra == 'dev'
-Requires-Dist: pytest ; extra == 'dev'
+Requires-Dist: black; extra == "dev"
+Requires-Dist: bumpver; extra == "dev"
+Requires-Dist: isort; extra == "dev"
+Requires-Dist: pip-tools; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Provides-Extra: all
+Requires-Dist: keyring; extra == "all"
+Requires-Dist: openpyxl; extra == "all"
+Requires-Dist: pandas; extra == "all"
+Requires-Dist: plotly; extra == "all"
+Requires-Dist: polars; extra == "all"
+Requires-Dist: pyarrow; extra == "all"
+Requires-Dist: pyreadstat; extra == "all"
+Requires-Dist: pyyaml; extra == "all"
+Requires-Dist: requests; extra == "all"
+Requires-Dist: sqlalchemy; extra == "all"
 
 # Tools Onderzoek & Statistiek
 
@@ -63,5 +63,12 @@ Instructions on building a package can be found [here](https://packaging.python.
 
 - make a pypi account
 - ask to be added as collaborator to toolsos
-- first update twine: py -m pip install --upgrade twin
-- upload to pypi: twine upload dist/*
+- first update twine: py -m pip install --upgrade twine
+- upload to pypi: twine upload dist/* --skip-existing
+
+## Install to local enviroment for testing
+
+- python -m venv local (maak een lokale venv aan)
+- local\Scripts\activate (activeer de venv)
+- pip install -e . (installer toolsos)
+- pip install -r local_requirements.txt (installeer de benodigde dependencies)

toolsos-0.2.6.dist-info/RECORD

@@ -0,0 +1,25 @@
+toolsos/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+toolsos/cbs_tools.py,sha256=361cogk0aIU4D4BKHaa7YSOBh64t5C3zrHlqtWx0iIc,3465
+toolsos/create_tables.py,sha256=43FHK3EERjumBtnGhngIdtthZzcc_Qi37lJ1MgATzBg,908
+toolsos/download.py,sha256=88hehmPL5m5d1nrcJjltuh4xrCItF5EYHaZdHOcSt-g,2652
+toolsos/geo.py,sha256=arapy_ol6_so8KZ5gJk9ywXysSz4W8ah-cjrJ3DuxAo,2419
+toolsos/helpers.py,sha256=VeOl-fLgePCbjEmAQdVmYe7z8OE1pISeDDuP1t5QSxM,997
+toolsos/polars_helpers.py,sha256=P3RHLQFeDL7-9U_Q1n4ma_NSkdYAiker4pnc57uluHw,770
+toolsos/database/database_connection.py,sha256=HCP8H_-iE2BOOQDp9v1HOgfUSX45XS-aqw7Nzf8drAU,4359
+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
+toolsos/huisstijl/graphs/bargraph.py,sha256=HYl01_euh23iDYSUhnAzYAXS0DhDpg9eLRjJEpeR6iU,2815
+toolsos/huisstijl/graphs/graph_styles.py,sha256=Z9LLH7j8ODTsYMYK0rslacphuiRDcq5_IpSjEEiK2VY,975
+toolsos/huisstijl/graphs/linegraph.py,sha256=dMUarRe31SXaY78OCXLy-PgnU8LlVJ9KkzKaHhDtuuI,698
+toolsos/huisstijl/graphs/piegraph.py,sha256=aEFiEM-9QuhBOjKHSXVuE5bTh-8uucq4FP6O8Vk1vZI,703
+toolsos/huisstijl/graphs/styler.py,sha256=-uZ7pjY1G39XvmaGHQd31gPRxjxmJGhYZk8xhy2JUWc,6623
+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=2FO-ByLjgs-DbNgem3cDfYJbLbIDzRDqXtjL75WN7kY,24054
+toolsos-0.2.6.dist-info/METADATA,sha256=Fm7Ng8JDYMiDD3Ccm5AYGlGrl3QPZGmRMHC6oNA5o5o,2683
+toolsos-0.2.6.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+toolsos-0.2.6.dist-info/top_level.txt,sha256=2ClEjUBbtfDQ8oPwvWRy1Sz2nrkLCXlg0mHaMdCWia0,8
+toolsos-0.2.6.dist-info/RECORD,,

{toolsos-0.1.4.dist-info → toolsos-0.2.6.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (75.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

toolsos-0.1.4.dist-info/RECORD

@@ -1,24 +0,0 @@
-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/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
-toolsos/huisstijl/graphs/bargraph.py,sha256=02-2UCnGyvSKXRSOt-f5WuYu8_-6x9tFEkSi-FdD654,2582
-toolsos/huisstijl/graphs/graph_styles.py,sha256=fuJUp0ZrZMhaXhHbfBJwOlPLVcCnKU_9MSfw6eddfCI,593
-toolsos/huisstijl/graphs/linegraph.py,sha256=eiFNV_bXYM9G-HH0NywPO6WHI9eOZ91kNXoO3aiAvfE,416
-toolsos/huisstijl/graphs/piegraph.py,sha256=Pzc3vrbvlkv40V3OYWh6bDDc5arRRwJq7dfRzplPKWY,571
-toolsos/huisstijl/graphs/styler.py,sha256=0Mm37y_bkSy8mRtNzUgYfW_vrYZrV6_h1GLqQ8y8bXI,3434
-toolsos/huisstijl/tables/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-toolsos/huisstijl/tables/table_styles.py,sha256=oYU6GJcfqlKpZof5PUjPsA7woJ3Tew78CHPyT0_jY6w,1343
-toolsos/huisstijl/tables/tables.py,sha256=1x4htBUrX8FUWSmPiOI7nCNm9R4NYv-J-cK33lOXKpM,19462
-toolsos-0.1.4.dist-info/METADATA,sha256=f5Vf3pkNPx8k2rJSziNvA5wNT7neRghAb1-xFe6wYsA,2417
-toolsos-0.1.4.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-toolsos-0.1.4.dist-info/top_level.txt,sha256=2ClEjUBbtfDQ8oPwvWRy1Sz2nrkLCXlg0mHaMdCWia0,8
-toolsos-0.1.4.dist-info/RECORD,,