Initial charts

.gitignore

@@ -1,2 +1,3 @@
 *.py[cod]
-*.html
+*.html
+out

chart_utils.py

@@ -0,0 +1,34 @@
+from bokeh import models as bm, plotting as bp
+from bokeh.transform import factor_cmap
+from pandas import DataFrame
+
+from data_utils import get_categorical_stats
+
+gender_colormap = factor_cmap("Sukupuoli", ["#4834d4", "#eb4d4b"], ["mies", "nainen"])
+
+
+def get_df_hover_tool(df: DataFrame):
+    return bm.HoverTool(tooltips=[(c, f"@{{{c}}}") for c in df.columns])
+
+
+def set_yaxis_cash(plot):
+    plot.yaxis.axis_label = "Vuositulot"
+    plot.yaxis[0].formatter = bm.NumeralTickFormatter(format="€0")
+
+
+def get_categorical_stats_plot(df, *, category):
+    df = get_categorical_stats(df, category, "Vuositulot")
+    df.reset_index(inplace=True)
+    df[category] = df[category].astype("category")
+    plot = bp.figure(
+        title=f"{category}/tulot", x_range=list(df[category].cat.categories)
+    )
+    set_yaxis_cash(plot)
+    plot.vbar(df[category], 0.4, df["max"], df["min"], color="#a4b0be")
+    plot.line(
+        df[category], df["median"], legend_label="median", color="#1289A7", line_width=4
+    )
+    plot.line(
+        df[category], df["mean"], legend_label="mean", color="#B53471", line_width=4
+    )
+    return plot

data_utils.py

@@ -0,0 +1,13 @@
+import pandas as pd
+
+
+def get_categorical_stats(
+    df: pd.DataFrame, category_col: str, value_col: str
+) -> pd.DataFrame:
+    # Drop records where value is not numeric before grouping...
+    df = df.copy()
+    df[value_col] = pd.to_numeric(df[value_col], errors="coerce")
+    df = df[df[value_col].notna() & df[value_col] > 0]
+    # ... then carry on.
+    group = df[[category_col, value_col]].groupby(category_col)
+    return group[value_col].agg(["mean", "min", "max", "median"])

generate_charts.py

@@ -0,0 +1,50 @@
+import bokeh.plotting as bp
+import bokeh.models as bm
+import bokeh.layouts as bl
+from pandas import DataFrame
+
+from chart_utils import (
+    gender_colormap,
+    get_df_hover_tool,
+    set_yaxis_cash,
+    get_categorical_stats_plot,
+)
+from data_ingest import read_data
+
+plot_funcs = set()
+
+
+def plot_this(fn):
+    """
+    Decorator for marking a function as a plot generator.
+    """
+    plot_funcs.add(fn)
+
+
+@plot_this
+def plot_kokemus_tulot(df: DataFrame):
+    source = bm.ColumnDataSource(df)
+    plot = bp.figure(title="Kokemus/Tulot")
+    plot.add_tools(get_df_hover_tool(df))
+    plot.xaxis.axis_label = "Työkokemus (v)"
+    set_yaxis_cash(plot)
+    plot.circle(
+        x="Työkokemus", y="Vuositulot", source=source, color=gender_colormap, size=10
+    )
+    return plot
+
+
+@plot_this
+def plot_ika_tulot(df: DataFrame):
+    return get_categorical_stats_plot(df, category="Ikä")
+
+
+def main():
+    df = read_data()
+    plots = [func(df) for func in sorted(plot_funcs, key=lambda f: f.__name__)]
+    bp.output_file("out/charts.html", title="Koodiklinikan Palkkakysely")
+    bp.save(bl.column(plots))
+
+
+if __name__ == "__main__":
+    main()