examples

examples

Module defines a method for making sample data and defines a

Channels

Bases: StrEnum

Attributes:

Name	Type	Description
time	str	'time'
wave1	str	'wave1'
wave2	str	'wave2'
wave3	str	'wave3'

example_data_product_generator

example_data_product_generator(workdir: Path) -> ProductList

Processes the generated sample data in given workdir returning several types of data products.

Parameters:

Name	Type	Description	Default
workdir	Path	Directory containing sample data.	required

Source code in src/trendify/examples.py

def example_data_product_generator(workdir: Path) -> trendify.ProductList:
    """
    Processes the generated sample data in given workdir returning several types of data products.

    Args:
        workdir (Path): Directory containing sample data.
    """
    products = []

    df = pd.read_csv(workdir.joinpath("results.csv"))
    df = df.set_index(Channels.time.name, drop=True)

    colors = list(plt.rcParams["axes.prop_cycle"].by_key()["color"])
    linestyles = ["-", ":", (0, (3, 1, 1, 1))]

    traces = [
        trendify.Trace2D.from_xy(
            x=df.index,
            y=df[col].values,
            tags=["trace_plot"],
            pen=trendify.Pen(
                label=col,
                color=colors[list(Channels).index(col)],
                linestyle=linestyles[i % len(linestyles)],
            ),
            format2d=trendify.Format2D(
                grid=trendify.Grid.from_theme(trendify.GridTheme.MATLAB),
                scale_x=trendify.AxisScale.LINEAR,
                scale_y=trendify.AxisScale.LINEAR,
            ),
        ).append_to_list(products)
        for i, col in enumerate(df.columns)
    ]

    traces = [
        trendify.Trace2D.from_xy(
            x=df.index,
            y=transform(df[col].values, trendify.AxisScale.LOG),
            tags=["trace_plot_log_y"],
            pen=trendify.Pen(
                label=col,
                color=colors[list(Channels).index(col)],
                linestyle=linestyles[i % len(linestyles)],
            ),
            format2d=trendify.Format2D(
                legend=trendify.Legend(
                    title="example",
                    loc=trendify.LegendLocation.CENTER_RIGHT,
                    framealpha=0,
                ),
                grid=trendify.Grid.from_theme(trendify.GridTheme.MATLAB),
                scale_x=trendify.AxisScale.LINEAR,
                scale_y=trendify.AxisScale.LOG,
            ),
        ).append_to_list(products)
        for i, col in enumerate(df.columns)
    ]

    traces = [
        trendify.Trace2D.from_xy(
            x=transform(df.index, trendify.AxisScale.LOG),
            y=transform(df[col].values, trendify.AxisScale.LOG),
            tags=["trace_plot_log_xy"],
            pen=trendify.Pen(
                label=col,
                color=colors[list(Channels).index(col)],
                linestyle=linestyles[i % len(linestyles)],
            ),
            format2d=trendify.Format2D(
                legend=trendify.Legend(
                    fancybox=False,
                    loc=trendify.LegendLocation.CENTER,
                    edgecolor="red",
                    framealpha=1,
                ),
                grid=trendify.Grid.from_theme(trendify.GridTheme.MATLAB),
                scale_x=trendify.AxisScale.LOG,
                scale_y=trendify.AxisScale.LOG,
            ),
        ).append_to_list(products)
        for i, col in enumerate(df.columns)
    ]

    traces = [
        trendify.Trace2D.from_xy(
            x=transform(df.index, trendify.AxisScale.LOG),
            y=df[col].values,
            tags=["trace_plot_log_x"],
            pen=trendify.Pen(
                label=col,
                color=colors[list(Channels).index(col)],
                linestyle=linestyles[i % len(linestyles)],
            ),
            format2d=trendify.Format2D(
                legend=trendify.Legend(visible=False),
                grid=trendify.Grid.from_theme(trendify.GridTheme.MATLAB),
                scale_x=trendify.AxisScale.LOG,
                scale_y=trendify.AxisScale.LINEAR,
            ),
        ).append_to_list(products)
        for i, col in enumerate(df.columns)
    ]

    for trace in traces:
        trendify.Point2D(
            x=workdir.name,
            y=len(trace.y),
            marker=trendify.Marker(
                size=10,
                label=trace.pen.label,
                color=trace.pen.color,
            ),
            format2d=trendify.Format2D(title_fig="N Points"),
            tags=["scatter_plot"],
        ).append_to_list(products)

    for name, series in df.items():
        trendify.TableEntry(
            row=workdir.name,
            col=name,
            value=len(series),
            tags=["table"],
            unit=None,
        ).append_to_list(products)

        trendify.HistogramEntry(
            tags=["histogram"],
            value=series.mean(),
            format2d=trendify.Format2D(
                title_fig="Idk lol",
                legend=trendify.Legend(
                    loc=trendify.LegendLocation.UPPER_LEFT,
                    bbox_to_anchor=(1.05, 1),
                ),
                label_x="Series value",
                label_y="Counts",
                grid=trendify.Grid.from_theme(trendify.GridTheme.MATLAB),
            ),
            style=trendify.HistogramStyle(alpha_face=1),
        ).append_to_list(products)

        trendify.AxLine(
            tags=["histogram"],
            value=series.mean(),
            orientation=trendify.LineOrientation.VERTICAL,
            pen=trendify.Pen(color="r", label="mean", zorder=2),
        ).append_to_list(products)

    return products

make_example_data

make_example_data(workdir: Path, n_folders: int = 10)

Makes some sample data from which to generate products

Parameters:

Name	Type	Description	Default
workdir	Path	Directory in which the sample data is to be generated	required
n_folders	int	Number of sample data files to generate (in separate subfolders).	10

Source code in src/trendify/examples.py

def make_example_data(workdir: Path, n_folders: int = 10):
    """
    Makes some sample data from which to generate products

    Args:
        workdir (Path): Directory in which the sample data is to be generated
        n_folders (int): Number of sample data files to generate (in separate subfolders).
    """
    models_dir = workdir.joinpath("models")
    models_dir.mkdir(parents=True, exist_ok=True)

    for n in range(n_folders):
        subdir = models_dir.joinpath(str(n))
        subdir.mkdir(exist_ok=True, parents=True)

        n_samples = np.random.randint(low=40, high=50)
        t = np.linspace(0, 1, n_samples)
        periods = [1, 2, 3]
        amplitudes = np.random.uniform(low=0.5, high=1.5, size=3)

        n_inputs = {"n_samples": n_samples}
        p_inputs = {f"p{n}": p for n, p in enumerate(periods)}
        a_inputs = {f"a{n}": a for n, a in enumerate(amplitudes)}
        inputs = {}
        inputs.update(n_inputs)
        inputs.update(p_inputs)
        inputs.update(a_inputs)
        pd.Series(inputs).to_csv(subdir.joinpath("stdin.csv"), header=False)

        rng = np.random.default_rng(seed=42)
        noise_level = 0.05
        d = [t] + [
            a * np.sin(t * (2 * np.pi / p)) + noise_level * rng.normal(size=len(t))
            for p, a in zip(periods, amplitudes)
        ]
        df = pd.DataFrame(np.array(d).transpose(), columns=[e.name for e in Channels])
        df.to_csv(subdir.joinpath("results.csv"), index=False)

    csv_files = list(models_dir.glob("**/stdin.csv"))
    csv_files.sort()
    input_series = []
    for csv in csv_files:
        series: pd.Series = pd.read_csv(csv, index_col=0, header=None).squeeze()
        series.name = int(csv.parent.stem)
        input_series.append(series)

make_sample_data

make_sample_data()

Generates sample data to run the trendify code on

Source code in src/trendify/examples.py

def make_sample_data():
    """
    Generates sample data to run the trendify code on
    """
    from trendify.examples import make_example_data
    import argparse

    parser = argparse.ArgumentParser(
        prog="make_sample_data_for_trendify",
    )
    parser.add_argument(
        "-wd",
        "--working-directory",
        required=True,
        help="Directory to be created and filled with sample data from a batch run",
    )
    parser.add_argument(
        "-n",
        "--number-of-data-sets",
        type=int,
        default=5,
        help="Number of sample data sets to generate",
    )
    args = parser.parse_args()
    make_example_data(
        workdir=Path(args.working_directory),
        n_folders=args.number_of_data_sets,
    )