tesorotools-python 0.0.7__py2.py3-none-any.whl → 0.0.8__py2.py3-none-any.whl

tesorotools/artists/__init__.py

@@ -0,0 +1,5 @@
+import matplotlib.style
+
+from ..utils.globals import STYLE_SHEET
+
+matplotlib.style.use(STYLE_SHEET)

tesorotools/artists/barh_plot.py

@@ -0,0 +1,310 @@
+from enum import Enum
+from pathlib import Path
+from typing import Any
+
+import matplotlib.pyplot as plt
+import pandas as pd
+from matplotlib.container import BarContainer
+from matplotlib.ticker import FuncFormatter
+
+from tesorotools.offsets.offsets import Difference, FloatingOffset, Stat
+from tesorotools.offsets.outliers import flag_outliers
+from tesorotools.utils.globals import DEBUG
+from tesorotools.utils.matplotlib import (
+    PLOT_CONFIG,
+    format_annotation,
+    load_fonts,
+)
+
+BARH_CONFIG: dict[str, Any] = PLOT_CONFIG["barh"]
+AX_CONFIG: dict[str, Any] = PLOT_CONFIG["ax"]
+FIG_CONFIG: dict[str, Any] = PLOT_CONFIG["figure"]
+
+load_fonts()
+
+
+class Column(Enum):
+    VALUE = "value"
+    AXIS = "axis"
+    DEVIATION = "deviation"
+    COLOR = "color"
+    ALPHA = "alpha"
+
+
+def _style_spines(
+    ax: plt.Axes,
+    decimals: int,
+    units: str,
+    *,
+    color: str,
+    linewidth: str,
+):
+    ax.grid(visible=True, axis="x")
+    for spine in ax.spines.values():
+        spine.set_color(color)
+        spine.set_linewidth(linewidth)
+    ax.xaxis.set_major_formatter(
+        FuncFormatter(lambda x, _: format_annotation(x, decimals, units))
+    )
+    ax.tick_params(axis="both", which="major")
+    for tick in ax.get_xticklines():
+        tick.set_markeredgecolor(color)
+    for tick in ax.get_yticklines():
+        tick.set_markeredgecolor(color)
+
+
+def _style_baseline(ax: plt.Axes, **baseline_config):
+    color: str = baseline_config["color"]
+    left_lim, right_lim = ax.get_xlim()
+    ax.set_xlim(left=min(0, left_lim), right=max(0, right_lim))
+    left_lim, right_lim = ax.get_xlim()
+    if left_lim == 0:
+        ax.spines["left"].set_edgecolor(color)
+    elif right_lim == 0:
+        ax.spines["right"].set_edgecolor(color)
+    else:
+        ax.axvline(x=0, **baseline_config)
+
+
+def _collect_series(
+    blocks: dict[str, Any] | None, series: dict[str, str] | None
+) -> dict[str, str]:
+    if series is None and blocks is None:
+        raise ValueError("blocks and series cannot be both missing")
+    if series is None and blocks is not None:
+        return _collect_block_series(blocks)
+    else:
+        return series
+
+
+def _collect_block_series(blocks: dict[str, Any]) -> dict[str, str]:
+    series = {}
+    for _, block_cfg in blocks.items():
+        series = series | block_cfg["series"]
+    return series
+
+
+def _infer_colors(
+    value_series: pd.Series, blocks: dict[str, Any] | None
+) -> pd.Series:
+    color_series: pd.Series = pd.Series(
+        index=value_series.index, name=Column.COLOR.value, dtype=str
+    )
+    if blocks is not None:
+        for idx, block_cfg in enumerate(blocks.values()):
+            block_series: dict[str, str] = block_cfg["series"]
+            color_series.loc[block_series.keys()] = f"C{idx}"
+    else:
+        color_series[value_series >= 0] = "C0"
+        color_series[value_series < 0] = "C1"
+    return color_series
+
+
+def _highlight_series(
+    alias: dict[str, str], value_series: pd.Series
+) -> pd.Series:
+    alpha_series: pd.Series = pd.Series(
+        index=value_series.index, name=Column.ALPHA.value
+    )
+    alpha_series.loc[:] = 1
+    high_series = [k for k, v in alias.items() if v.endswith("*")]
+    alpha_series.loc[high_series] = BARH_CONFIG["highlight_factor"]
+    return alpha_series
+
+
+def _format_yaxis(
+    alias: dict[str, str],
+    axis_format: dict[str, Any],
+    value_series: pd.Series,
+    axis_series: pd.Series | None,
+) -> pd.Series:
+    # format y axis ticker labels
+    renamer = {_: label.replace("*", "") for _, label in alias.items()}
+    value_series = value_series.rename(renamer)
+    if axis_format is not None:
+        decimals: int = axis_format["decimals"]
+        units: str = axis_format["units"]
+        axis_series: pd.Series = axis_series.rename(renamer).apply(
+            lambda x: format_annotation(x, decimals, units)
+        )
+        value_series = value_series.rename(
+            lambda x: f"{x} ({axis_series.loc[x]})"
+        )
+    return value_series
+
+
+def _annotate(
+    fig: plt.Figure,
+    ax: plt.Axes,
+    bar_container: BarContainer,
+    *,
+    decimals: int,
+    units: str,
+):
+    # annotate
+    labels = ax.bar_label(
+        container=bar_container,
+        fmt=lambda x: format_annotation(x, decimals, units),
+        padding=BARH_CONFIG["padding"],
+    )
+
+    # rescale
+    fig.canvas.draw_idle()
+    for label in labels:
+        bbox = label.get_window_extent()
+        bbox_data = bbox.transformed(ax.transData.inverted())
+        ax.update_datalim(bbox_data.corners())
+        ax.autoscale_view()
+
+
+def _plot_barh_chart(
+    out_file: Path,
+    standard_dict: dict[Column, pd.Series | None],
+    alias: dict[str, str],
+    sorted: bool,
+    format: dict,
+    annot_format: dict,
+    axis_format: dict | None = None,
+    blocks: dict | None = None,
+    **kwargs,
+):
+    # infer colors
+    value_series: pd.Series = standard_dict[Column.VALUE]
+    color_series: pd.Series = _infer_colors(value_series, blocks)
+    alpha_series: pd.Series = _highlight_series(alias, value_series)
+
+    # format y axis ticker labels
+    axis_series = standard_dict[Column.AXIS]
+    value_series = _format_yaxis(alias, axis_format, value_series, axis_series)
+    color_series.index = value_series.index
+    alpha_series.index = value_series.index
+
+    data: pd.DataFrame = pd.concat(
+        [value_series, color_series, alpha_series], axis=1
+    )
+
+    # sort if required
+    if sorted:
+        data = data.sort_values(by=Column.VALUE.value)
+
+    # plot
+    fig = plt.figure(**FIG_CONFIG)
+    ax = fig.add_subplot()
+
+    bar_container: BarContainer = ax.barh(
+        y=data.index,
+        width=data[Column.VALUE.value],
+        color=data[Column.COLOR.value],
+    )
+    for bar, alpha in zip(bar_container, data[Column.ALPHA.value]):
+        bar.set_alpha(alpha)
+
+    _annotate(fig, ax, bar_container, **annot_format)
+    _style_spines(ax, **format, **AX_CONFIG["spines"])
+    _style_baseline(ax, **AX_CONFIG["baseline"])
+
+    fig.savefig(out_file)
+
+
+def _normalize_from_flash(
+    flash: pd.DataFrame,
+    axis: bool,
+    *,
+    date: str | pd.Timestamp | None,
+    offset: str,
+    difference: str,
+    deviations: bool,
+    units_bar: str,
+    units_axis: str,
+) -> dict[Column, pd.Series | None]:
+
+    # format parameters
+    date: pd.Timestamp = (
+        flash.index.get_level_values(level=0).max()
+        if date is None
+        else pd.to_datetime(date)
+    )
+    offset: FloatingOffset = FloatingOffset(offset)
+    difference: Difference = Difference(difference)
+
+    # value column
+    values_series: pd.Series = flash.loc[
+        (date, offset.value, difference.value, Stat.VALUE.value),
+        :,
+    ].copy()
+    values_series.name = Column.VALUE.value
+    values_series = (
+        values_series * 100 if difference is Difference.REL else values_series
+    )
+    values_series = (
+        values_series * 100
+        if (difference is Difference.ABS and units_bar == "p.b.")
+        else values_series
+    )
+
+    # axis column
+    if axis:
+        axis_series: pd.Series = flash.loc[
+            (
+                date,
+                FloatingOffset.NO.value,
+                Difference.NO.value,
+                Stat.VALUE.value,
+            ),
+            :,
+        ].copy()
+        axis_series = (
+            axis_series * 100
+            if (difference is Difference.ABS and units_axis == "p.b.")
+            else axis_series
+        )
+
+        axis_series.name = Column.AXIS.value
+    else:
+        axis_series = None
+
+    # deviations column
+    if deviations:
+        deviations_df: pd.DataFrame = flash.loc[
+            (
+                date,
+                offset.value,
+                difference.value,
+                [Stat.VALUE.value, Stat.ROLL_AVG.value, Stat.ROLL_STD._value_],
+            ),
+            :,
+        ].T.copy()
+        deviations_df.columns = deviations_df.columns.get_level_values(level=-1)
+        deviations_df.columns.name = None
+        deviations_series: pd.Series = flag_outliers(deviations_df)
+        deviations_series.name = Column.DEVIATION.value
+    else:
+        deviations_series = None
+
+    return {
+        Column.VALUE: values_series,
+        Column.AXIS: axis_series,
+        Column.DEVIATION: deviations_series,
+    }
+
+
+def plot_barh_charts_from_flash(
+    flash: pd.DataFrame, config_dicts: dict[str, dict]
+):
+    for name, config in config_dicts.items():
+        blocks: dict[str, Any] = config.get("blocks", None)
+        series: dict[str, str] | None = config.get("series", None)
+        alias = _collect_series(blocks, series)
+        trimmed_flash: pd.DataFrame = flash.loc[:, alias.keys()]
+        flash_config: dict[str, Any] = config["flash"]
+        axis_format: dict[str, Any] = config.get("axis_format", None)
+        axis = axis_format is not None
+        standard_dict: dict[Column, pd.Series | None] = _normalize_from_flash(
+            trimmed_flash,
+            axis,
+            **flash_config,
+            units_bar=config["format"]["units"],
+            units_axis=config.get("axis_format", {"units": ""})["units"],
+        )
+        out_file = Path(DEBUG / "barh" / f"{name}.png")
+        _plot_barh_chart(out_file, standard_dict, alias, **config)

tesorotools/artists/line_plot.py

@@ -0,0 +1,114 @@
+import locale
+from pathlib import Path
+from typing import Any
+
+import matplotlib.pyplot as plt
+import pandas as pd
+from matplotlib.ticker import FuncFormatter
+
+locale.setlocale(locale.LC_ALL, "")
+
+from tesorotools.utils.globals import DEBUG
+from tesorotools.utils.matplotlib import (
+    PLOT_CONFIG,
+    format_annotation,
+    load_fonts,
+)
+
+load_fonts()
+
+LINE_PLOT_CONFIG: dict[str, Any] = PLOT_CONFIG["line"]
+AX_CONFIG: dict[str, Any] = PLOT_CONFIG["ax"]
+FIG_CONFIG: dict[str, Any] = PLOT_CONFIG["figure"]
+
+
+def _style_spines(
+    ax: plt.Axes,
+    decimals: int,
+    units: str,
+    *,
+    color: str,
+    linewidth: str,
+):
+    ax.grid(visible=True, axis="y")
+    for spine in ax.spines.values():
+        spine.set_color(color)
+        spine.set_linewidth(linewidth)
+    ax.yaxis.tick_right()
+    ax.yaxis.set_major_formatter(
+        FuncFormatter(lambda y, _: format_annotation(y, decimals, units))
+    )
+    ax.set_xlabel("")
+
+    ax.tick_params(which="minor", size=0, width=0)
+    ax.tick_params(axis="both", which="major")
+    for tick in ax.get_xticklines():
+        tick.set_markeredgecolor(color)
+    for tick in ax.get_yticklines():
+        tick.set_markeredgecolor(color)
+
+
+def _style_baseline(ax: plt.Axes, reference: float = 0, **baseline_config):
+    color: str = baseline_config["color"]
+    bottom_lim, top_lim = ax.get_ylim()
+    ax.set_ylim(bottom=min(reference, bottom_lim), top=max(reference, top_lim))
+    bottom_lim, top_lim = ax.get_ylim()
+    if bottom_lim == reference:
+        ax.spines["bottom"].set_edgecolor(color)
+    elif top_lim == reference:
+        ax.spines["top"].set_edgecolor(color)
+    else:
+        ax.axhline(y=reference, **baseline_config)
+
+
+def plot_line_chart(
+    out_name: Path,
+    data: pd.DataFrame,
+    *,
+    base_100: bool,
+    annotate: bool,
+    format: dict[str, Any],
+    **kwargs,
+):
+    if base_100:
+        data = data / data.iloc[0, :] * 100
+    if format["units"] == "p.b.":
+        data = data * 100
+    fig = plt.figure(**FIG_CONFIG)
+    ax = fig.add_subplot()
+    data.plot(ax=ax)
+    if annotate:
+        pass
+
+    reference = 100 if base_100 else 0
+    _style_spines(ax, **format, **AX_CONFIG["spines"])
+    _style_baseline(ax, reference, **AX_CONFIG["baseline"])
+    ax.legend(
+        loc="upper center",
+        bbox_to_anchor=(0.5, LINE_PLOT_CONFIG["legend_sep"]),
+        ncol=(
+            kwargs["legend"]["ncol"]
+            if kwargs is not None and kwargs.get("legend", None) is not None
+            else LINE_PLOT_CONFIG["ncol"]
+        ),
+    )
+
+    fig.savefig(out_name)
+
+
+def plot_line_charts(data: pd.DataFrame, config_dicts: dict[str, Any]):
+    for name, config in config_dicts.items():
+        start_date: pd.Timestamp = pd.to_datetime(config["start_date"])
+        end_date_str: str | None = config["end_date"]
+        end_date: pd.Timestamp = (
+            data.index.max()
+            if end_date_str is None
+            else pd.to_datetime(end_date_str)
+        )
+        series: dict[str, str] = config["series"]
+        trimmed_data: pd.DataFrame = data.loc[
+            slice(start_date, end_date), series.keys()
+        ]
+        trimmed_data = trimmed_data.rename(columns=series)
+        out_name: Path = DEBUG / "line" / f"{name}.png"
+        plot_line_chart(out_name, trimmed_data, **config)

tesorotools/artists/table.py

@@ -0,0 +1,199 @@
+from math import floor
+from typing import Any
+
+import pandas as pd
+
+from tesorotools.dependencies.resolution import collect_series
+from tesorotools.offsets.outliers import flag_outliers
+from tesorotools.utils.globals import DEBUG
+from tesorotools.utils.matplotlib import format_annotation, is_zero
+
+# this file is by far the worst and most spaghettified, must be rewritten
+
+# to global config
+GOOD: str = "00c800"
+BAD: str = "c80000"
+THRESHOLD: float = 1
+SHADE_LEVELS = 2
+
+
+def _shade_intensity(
+    ratio: float, shade_levels: int = 2, continuous: bool = False
+) -> str:
+    # intensity may vary from 150 (highest) to 255 (lowest), a grand difference of 105
+    # there are SHADE_LEVELS levels, so increments will be of 105/SHADE_LEVELS
+    corrected_ratio: float = min(ratio, shade_levels)
+    corrected_ratio: float = (
+        floor(corrected_ratio) if not continuous else corrected_ratio
+    )
+    increment: float = (corrected_ratio - 1) * (105 / shade_levels)
+    intensity: float = 255 - increment
+    intensity_hex: str = f"{int(intensity):x}"
+    return intensity_hex
+
+
+def _generate_column(
+    column_data: pd.Series,
+    column_cfg: dict[str, Any],
+    outliers_flags: pd.Series | None = None,
+):
+    # TODO: factor out
+    # data
+    if column_cfg["show_units_in_title"]:
+        column_data.name = f"{column_cfg["name"]} ({column_cfg["unit"]})"
+    else:
+        column_data.name = column_cfg["name"]
+    column_cfg["formatted_name"] = column_data.name
+
+    unit = (
+        column_cfg["unit"]
+        if column_cfg["show_units_in_cell"] and column_cfg["unit"] is not None
+        else ""
+    )
+    scaled_data: pd.Series = column_data * column_cfg["scale"]
+    formatted_data = scaled_data.apply(
+        lambda x: format_annotation(
+            x, decimals=column_cfg["decimals"], units=unit
+        )
+    )
+    zeros: pd.Series = scaled_data.apply(
+        lambda x: is_zero(x, decimals=column_cfg["decimals"])
+    )
+    positives: pd.Series = scaled_data > 0
+    negatives: pd.Series = scaled_data < 0
+
+    # colors
+    colors_cfg: bool = column_cfg["colors"]
+    color_data: pd.Series = pd.Series(
+        index=formatted_data.index, name=column_data.name, dtype=str
+    )
+    if colors_cfg:
+        positive_good: bool = column_cfg["positive_good"]
+        color_data[positives] = GOOD if positive_good else BAD
+        color_data.loc[negatives] = BAD if positive_good else GOOD
+        color_data.loc[zeros.values] = pd.NA
+
+    # shades
+    shade_data: pd.Series = pd.Series(
+        index=formatted_data.index, name=column_data.name, dtype=str
+    )
+    if outliers_flags is not None:
+        thresholds: pd.Series = abs(outliers_flags / THRESHOLD)
+        intensities: pd.Series = thresholds.apply(
+            lambda x: _shade_intensity(x, SHADE_LEVELS)
+        )
+        shade_data[(thresholds >= 1) & (outliers_flags > 0)] = intensities[
+            (thresholds >= 1) & (outliers_flags > 0)
+        ].apply(lambda x: f"00{x}00" if positive_good else f"{x}0000")
+        shade_data[(thresholds >= 1) & (outliers_flags < 0)] = intensities[
+            (thresholds >= 1) & (outliers_flags < 0)
+        ].apply(lambda x: f"{x}0000" if positive_good else f"00{x}00")
+
+    return formatted_data, color_data, shade_data
+
+
+def _generate_block(block_data: pd.DataFrame, block_cfg: dict[str, Any]):
+    columns: dict[str, Any] = block_cfg["columns"]
+    formatted_columns: list[pd.Series] = []
+    color_columns: list[pd.Series] = []
+    shade_columns: list[pd.Series] = []
+    sort_idx: pd.Index | None = None
+    for column_name, column_cfg in columns.items():
+        last_date: pd.Timestamp = block_data.index.get_level_values(
+            level=0
+        ).max()
+        block_data = block_data.rename(columns=block_cfg["series"])
+        offset: str = column_cfg["offset"]
+        difference: str = column_cfg["difference"]
+        stat: str = column_cfg["stat"]
+        outliers: bool = column_cfg["outliers"]
+
+        stat_data = block_data.loc[
+            (last_date, offset, difference, slice(None)), :
+        ]
+        stat_data.index = stat_data.index.get_level_values(level=-1)
+
+        outliers_flags: pd.Series | None = None
+        if outliers:
+            outliers_flags = flag_outliers(stat_data.T)
+
+        column_data: pd.Series = stat_data.loc[stat, :]
+        # sort capability
+        sort: str = block_cfg.get("sort", None)
+        if sort is not None and column_name == sort:
+            column_data: pd.Series = column_data.sort_values(ascending=False)
+            sort_idx = column_data.index
+        formatted_column, color_column, shade_column = _generate_column(
+            column_data, column_cfg, outliers_flags
+        )
+        formatted_columns.append(formatted_column)
+        color_columns.append(color_column)
+        shade_columns.append(shade_column)
+
+    if sort_idx is not None:
+        formatted_columns = [s.reindex(sort_idx) for s in formatted_columns]
+        color_columns = [s.reindex(sort_idx) for s in color_columns]
+        shade_columns = [s.reindex(sort_idx) for s in shade_columns]
+
+    formatted_block: pd.DataFrame = pd.concat(formatted_columns, axis=1)
+    color_block: pd.DataFrame = pd.concat(color_columns, axis=1)
+    shade_block: pd.DataFrame = pd.concat(shade_columns, axis=1)
+
+    formatted_block.columns.name = block_cfg["title"]
+    color_block.columns.name = block_cfg["title"]
+    shade_block.columns.name = block_cfg["title"]
+    return formatted_block, color_block, shade_block
+
+
+def generate_table(table_data: pd.DataFrame, table_cfg: dict[str, Any]):
+    blocks: dict[str, dict] = table_cfg["blocks"]
+    formatted_blocks: list[pd.DataFrame] = []
+    color_blocks: list[pd.DataFrame] = []
+    shade_blocks: list[pd.DataFrame] = []
+    axis = 0 if table_cfg["axis"] == "vertical" else 1
+    # sorting capabilities
+    for block_name, block_cfg in blocks.items():
+        series_dict: dict[str, str] = block_cfg["series"]
+        block_data: pd.DataFrame = table_data.loc[:, series_dict.keys()]
+        formatted_block, color_block, shade_block = _generate_block(
+            block_data, block_cfg
+        )
+        formatted_blocks.append(formatted_block)
+        color_blocks.append(color_block)
+        shade_blocks.append(shade_block)
+    formatted_table = pd.concat(
+        formatted_blocks,
+        axis=axis,
+        keys=[
+            formatted_block.columns.name for formatted_block in formatted_blocks
+        ],
+    )
+    color_table = pd.concat(
+        color_blocks,
+        axis=axis,
+        keys=[
+            formatted_block.columns.name for formatted_block in formatted_blocks
+        ],
+    )
+    shade_table = pd.concat(
+        shade_blocks,
+        axis=axis,
+        keys=[
+            formatted_block.columns.name for formatted_block in formatted_blocks
+        ],
+    )
+    return formatted_table, color_table, shade_table
+
+
+def generate_tables_from_flash(
+    flash: pd.DataFrame, config_dicts: dict[str, dict]
+):
+    for table_name, table_cfg in config_dicts.items():
+        series: list[str] = list(collect_series(table_cfg))
+        table_data: pd.DataFrame = flash.loc[:, series]
+        formatted_table, color_table, shade_table = generate_table(
+            table_data, table_cfg
+        )
+        formatted_table.to_feather(DEBUG / "table" / f"{table_name}.feather")
+        color_table.to_feather(DEBUG / "table" / f"{table_name}_color.feather")
+        shade_table.to_feather(DEBUG / "table" / f"{table_name}_shade.feather")