toolsos 0.2.7__tar.gz → 0.3.0__tar.gz

{toolsos-0.2.7 → toolsos-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: toolsos
-Version: 0.2.7
+Version: 0.3.0
 Summary: OS tools
 Author-email: OS <d.schmitz@amsterdam.nl>
 Keywords: tools,Onderzoek & Statistiek
@@ -26,6 +26,7 @@ Requires-Dist: pyreadstat; extra == "all"
 Requires-Dist: pyyaml; extra == "all"
 Requires-Dist: requests; extra == "all"
 Requires-Dist: sqlalchemy; extra == "all"
+Requires-Dist: geopandas; extra == "all"
 
 # Tools Onderzoek & Statistiek
 

{toolsos-0.2.7 → toolsos-0.3.0}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "toolsos"
-version = "0.2.7"
+version = "0.3.0"
 description = "OS tools"
 readme = "README.md"
 authors = [{ name = "OS", email = "d.schmitz@amsterdam.nl" }]
@@ -47,6 +47,7 @@ all = [
     "pyyaml",
     "requests",
     "sqlalchemy",
+    "geopandas"
     ]
 
 # [project.urls]

{toolsos-0.2.7 → toolsos-0.3.0}/src/toolsos/geo.py

@@ -1,7 +1,10 @@
 from __future__ import annotations
 
+from pathlib import Path
 from typing import Any, Union
 
+import geopandas as gpd
+import pandas as pd
 import requests
 
 
@@ -43,6 +46,38 @@ def get_geo_json(
     return json
 
 
+def get_geo_dataframe(
+    level: str,
+    year: Union[int, Any],
+    with_water: bool = False,
+    mra: bool = False,
+    from_crs=4326,
+    to_crs=28992,
+):
+
+    gdf = gpd.GeoDataFrame.from_features(
+        get_geo_json(level=level, year=year, with_water=with_water, mra=mra)
+    )
+
+    gdf = gdf.set_crs(from_crs).to_crs(to_crs)
+
+    return gdf
+
+
+def merge_data_to_gdf(
+    data: str, gdf: gpd.GeoDataFrame, key_data: str = "code", key_gdf: str = "code"
+) -> gpd.GeoDataFrame:
+    p = Path(data)
+    if p.suffix == ".csv":
+        df = pd.read_csv(data)
+    elif p.suffix in [".xlsx", ".xls"]:
+        df = pd.read_excel(data)
+    else:
+        raise ValueError(f"File type not supported: {p.suffix}")
+
+    return gdf.merge(df, how="left", left_on=key_data, right_on=key_gdf)
+
+
 def extract_name_code_table(geo_json: dict[str, str]) -> dict[str, str]:
     """_summary_
 

{toolsos-0.2.7 → toolsos-0.3.0}/src/toolsos/helpers.py

@@ -24,16 +24,29 @@ def os_cut(
     start_label: str = "lager dan",
     end_label: str = "en hoger",
     add_edge: Optional[int] = None,
-    sep: str = " - ",
+    sep: str = " tot ",
+    na_value: Optional[str] = None,
+    unit: Optional[str] = None,
 ) -> pd.Series:
     # Add non_overlap to left edge/boundary
     if not add_edge:
         add_edge = 0
 
-    start_l = [f"{start_label} {bins[1]}"]
+    if not unit:
+        unit = ""
+
+    start_l = [f"{start_label} {bins[1]}{unit}"]
     inbetween_labels = [
-        f"{bins[i] + add_edge}{sep}{bins[i+1]}" for i in range(1, len(bins) - 2)
+        f"{bins[i] + add_edge}{unit}{sep}{bins[i+1]}{unit}"
+        for i in range(1, len(bins) - 2)
     ]
-    end_l = [f"{bins[-2]} {end_label}"]
+    end_l = [f"{bins[-2]}{unit} {end_label}"]
+
+    labels = start_l + inbetween_labels + end_l
+
+    categorized = pd.cut(x, bins=bins, labels=labels, include_lowest=True)  # type: ignore
+
+    if na_value:
+        categorized = categorized.cat.add_categories(na_value).fillna(na_value)
 
-    return pd.cut(x, bins=bins, labels=start_l + inbetween_labels + end_l)  # type: ignore
+    return categorized

toolsos-0.3.0/src/toolsos/huisstijl/maps/choropleth.py

@@ -0,0 +1,72 @@
+from typing import Any, Iterable, Optional
+
+import geopandas as gpd
+import matplotlib.pyplot as plt
+from matplotlib.colors import ListedColormap
+from matplotlib.patches import Patch
+
+
+def plot_choropleth(
+    gdf: gpd.GeoDataFrame,
+    column: str,
+    colors: Iterable[str],
+    column_label: Optional[str] = False,
+    column_label_kwargs: Any = None,
+    legend_title: Optional[str] = None,
+    edgecolor: str = "grey",
+    figsize: tuple[int, int] = (10, 8),
+    bbox_to_anchor: tuple[int, int] = (-0.05, 0),
+):
+    # plotten
+    fig, ax = plt.subplots(figsize=figsize)
+
+    gdf.plot(
+        column=column,
+        cmap=ListedColormap(colors),
+        ax=ax,
+        categorical=True,
+        edgecolor=edgecolor,
+        linewidth=0.2,
+    )
+
+    labels = gdf["categorieen"].cat.categories
+
+    if not column_label_kwargs:
+        column_label_kwargs = {}
+
+    if column_label:
+        for x, y, label in zip(
+            gdf.geometry.representative_point().x,
+            gdf.geometry.representative_point().y,
+            gdf[column_label],
+        ):
+            ax.annotate(
+                label,
+                xy=(x, y),
+                xytext=(0, 0),
+                textcoords="offset points",
+                **column_label_kwargs,
+            )
+
+    # Create custom legend using the 'colors' and 'labels' variables, with a grey border
+    legend_elements = [
+        Patch(facecolor=color, label=label, edgecolor="#b0b0b0")
+        for color, label in zip(colors, labels)
+    ]
+
+    # Move the legend to the bottom left outside the plot
+    ax.legend(
+        handles=legend_elements,
+        bbox_to_anchor=bbox_to_anchor,
+        loc="lower left",
+        title=legend_title,
+        frameon=False,
+    )
+
+    # lat/lon uit
+    ax.set_axis_off()
+
+    # laten zien
+    plt.tight_layout()
+
+    return fig, ax

{toolsos-0.2.7 → toolsos-0.3.0}/src/toolsos/huisstijl/tables/tables.py

@@ -278,7 +278,14 @@ def get_cols_id_with_pattern(df: pd.DataFrame, pattern: str) -> list[int]:
     Returns:
         list[int]: list with column indices matching pattern
     """
-    return [idx for idx, col in enumerate(df.columns) if re.findall(pattern, col)]
+
+    if isinstance(df.columns, pd.MultiIndex):
+        # Use the lowest level in the multi-index column
+        return [
+            idx for idx, col in enumerate(df.columns) if re.findall(pattern, col[-1])
+        ]
+    else:
+        return [idx for idx, col in enumerate(df.columns) if re.findall(pattern, col)]
 
 
 def get_string_cols_ids(df: pd.DataFrame) -> list[int]:
@@ -702,6 +709,7 @@ def format_worksheet(
                 "The number of widths defined in column_widths should be equal to the number of columsn in the dataframe"
             )
         col_widths = column_widths
+
     elif (autofit_columns == "column_names") or (autofit_columns is None):
         col_widths = get_max_col_widths(df)
     elif autofit_columns == "all_data":

{toolsos-0.2.7 → toolsos-0.3.0}/src/toolsos.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: toolsos
-Version: 0.2.7
+Version: 0.3.0
 Summary: OS tools
 Author-email: OS <d.schmitz@amsterdam.nl>
 Keywords: tools,Onderzoek & Statistiek
@@ -26,6 +26,7 @@ Requires-Dist: pyreadstat; extra == "all"
 Requires-Dist: pyyaml; extra == "all"
 Requires-Dist: requests; extra == "all"
 Requires-Dist: sqlalchemy; extra == "all"
+Requires-Dist: geopandas; extra == "all"
 
 # Tools Onderzoek & Statistiek
 

{toolsos-0.2.7 → toolsos-0.3.0}/src/toolsos.egg-info/SOURCES.txt

@@ -23,7 +23,9 @@ src/toolsos/huisstijl/graphs/linegraph.py
 src/toolsos/huisstijl/graphs/piegraph.py
 src/toolsos/huisstijl/graphs/styler.py
 src/toolsos/huisstijl/maps/__init__.py
+src/toolsos/huisstijl/maps/choropleth.py
 src/toolsos/huisstijl/tables/__init__.py
 src/toolsos/huisstijl/tables/table_helpers.py
 src/toolsos/huisstijl/tables/table_styles.py
-src/toolsos/huisstijl/tables/tables.py
+src/toolsos/huisstijl/tables/tables.py
+tests/test_tables.py

{toolsos-0.2.7 → toolsos-0.3.0}/src/toolsos.egg-info/requires.txt

@@ -10,6 +10,7 @@ pyreadstat
 pyyaml
 requests
 sqlalchemy
+geopandas
 
 [dev]
 black

toolsos-0.3.0/tests/test_tables.py

@@ -0,0 +1,56 @@
+import openpyxl
+import pandas as pd
+import pytest
+
+from toolsos.huisstijl.tables.tables import write_table, write_table_from_dict
+
+DATA = [["Noord", 1, 0.25], ["Zuid", 3, 0.75]]
+
+
+COLUMNS = ["stadsdeel", "bewoners", "perc_bewoners"]
+
+
+@pytest.fixture(scope="class")
+def workbook(data=DATA, columns=COLUMNS):
+    df1 = pd.DataFrame(data=DATA, columns=COLUMNS)
+
+    filename = "temp/singe_table.xlsx"
+    write_table(
+        df1, file=filename, header_row=0, perc_pattern="perc_bewoners", style="new"
+    )
+    return openpyxl.load_workbook(filename)
+
+
+class TestTable:
+    @pytest.fixture(autouse=True)
+    def setup(self, workbook):
+        self.workbook = workbook
+        self.ws = workbook.active
+
+    def test_data(self, data=DATA):
+        rows = [[c.value for c in row] for row in self.ws.iter_rows(2)]
+
+        assert all(src == written for src, written in zip(DATA, rows))
+
+    def test_data_header(self):
+        header = [[c.value for c in row] for row in self.ws.iter_rows(2)]
+
+        assert all(src == written for src, written in zip(DATA, header))
+
+    def test_background_color_header(self):
+        header_color = [
+            [c.fill.fgColor.value for c in row] for row in self.ws.iter_rows(max_row=1)
+        ]
+
+        assert all([[c == "004699" for c in row] for row in header_color])
+
+    # def test_text_color_header(self):
+    #     header_text_color = [[c.font.color.value for in row] in self.ws]
+
+    def test_formatting(self):
+        perc_values = [
+            [c.number_format for c in row]
+            for row in self.ws.iter_rows(min_row=2, min_col=3)
+        ]
+
+        all([[c == "'0.0%'" for c in row] for row in perc_values])