plothist 1.4.0__py3-none-any.whl → 1.6.0__py3-none-any.whl

plothist/examples/model_ex/model_all_comparisons_no_model_unc.py

@@ -0,0 +1,115 @@
+"""
+Data/model comparisons, no model uncertainty
+============================================
+
+All supported comparisons between data and model, without model uncertainty.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+from plothist import get_color_palette, make_hist
+
+# Define the histograms
+
+key = "variable_1"
+range = (-9, 12)
+category = "category"
+
+# Define masks
+signal_mask = df[category] == 7
+data_mask = df[category] == 8
+
+background_categories = [0, 1, 2]
+background_categories_labels = [f"c{i}" for i in background_categories]
+background_categories_colors = get_color_palette(
+    "cubehelix", len(background_categories)
+)
+
+background_masks = [df[category] == p for p in background_categories]
+
+# Make histograms
+data_hist = make_hist(df[key][data_mask], bins=50, range=range, weights=1)
+background_hists = [
+    make_hist(df[key][mask], bins=50, range=range, weights=1)
+    for mask in background_masks
+]
+
+# Optional: scale to data
+background_scaling_factor = data_hist.sum().value / sum(background_hists).sum().value
+background_hists = [background_scaling_factor * h for h in background_hists]
+
+###
+import numpy as np
+
+from plothist import (
+    add_text,
+    create_comparison_figure,
+    plot_comparison,
+    plot_data_model_comparison,
+    set_fitting_ylabel_fontsize,
+)
+
+fig, axes = create_comparison_figure(
+    figsize=(6, 13),
+    nrows=6,
+    gridspec_kw={"height_ratios": [3, 1, 1, 1, 1, 1]},
+    hspace=0.3,
+)
+background_sum = sum(background_hists)
+
+plot_data_model_comparison(
+    data_hist=data_hist,
+    stacked_components=background_hists,
+    stacked_labels=background_categories_labels,
+    stacked_colors=background_categories_colors,
+    xlabel="",
+    ylabel="Entries",
+    model_uncertainty=False,  # <--
+    comparison="ratio",
+    fig=fig,
+    ax_main=axes[0],
+    ax_comparison=axes[1],
+)
+
+add_text(
+    r"Multiple data-model comparisons, $\mathbf{without}$ model uncertainty",
+    ax=axes[0],
+)
+add_text(r'  $\mathbf{→}$ comparison = "ratio"', ax=axes[1], fontsize=13)
+
+for k_comp, comparison in enumerate(
+    ["split_ratio", "pull", "relative_difference", "difference"], start=2
+):
+    ax_comparison = axes[k_comp]
+
+    # Copy the original histogram and set the uncertainties of the copy to 0.
+    background_sum_copy = background_sum.copy()
+    background_sum_copy[:] = np.c_[
+        background_sum_copy.values(), np.zeros_like(background_sum_copy.values())
+    ]
+
+    plot_comparison(
+        data_hist,
+        background_sum_copy,
+        ax=ax_comparison,
+        comparison=comparison,
+        xlabel="",
+        h1_label="Data",
+        h2_label="Pred.",
+        h1_uncertainty_type="asymmetrical",
+    )
+    if comparison == "pull":
+        # Since the uncertainties of the model are neglected, the pull label is "(Data - Pred.)/sigma_Data"
+        ax_comparison.set_ylabel(r"$\frac{Data-Pred.}{\sigma_{Data}}$")
+    add_text(
+        rf'  $\mathbf{{→}}$ comparison = "{comparison}"',
+        ax=ax_comparison,
+        fontsize=13,
+    )
+    set_fitting_ylabel_fontsize(ax_comparison)
+
+axes[-1].set_xlabel(key)
+
+fig.savefig("model_all_comparisons_no_model_unc.svg", bbox_inches="tight")

plothist/examples/model_ex/model_examples_pull.py

@@ -0,0 +1,56 @@
+"""
+Pull plot
+=========
+
+Compare data and model with pulls.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+from plothist import get_color_palette, make_hist
+
+# Define the histograms
+
+key = "variable_1"
+range = (-9, 12)
+category = "category"
+
+# Define masks
+signal_mask = df[category] == 7
+data_mask = df[category] == 8
+
+background_categories = [0, 1, 2]
+background_categories_labels = [f"c{i}" for i in background_categories]
+background_categories_colors = get_color_palette(
+    "cubehelix", len(background_categories)
+)
+
+background_masks = [df[category] == p for p in background_categories]
+
+# Make histograms
+data_hist = make_hist(df[key][data_mask], bins=50, range=range, weights=1)
+background_hists = [
+    make_hist(df[key][mask], bins=50, range=range, weights=1)
+    for mask in background_masks
+]
+
+# Optional: scale to data
+background_scaling_factor = data_hist.sum().value / sum(background_hists).sum().value
+background_hists = [background_scaling_factor * h for h in background_hists]
+
+###
+from plothist import plot_data_model_comparison
+
+fig, ax_main, ax_comparison = plot_data_model_comparison(
+    data_hist=data_hist,
+    stacked_components=background_hists,
+    stacked_labels=background_categories_labels,
+    stacked_colors=background_categories_colors,
+    xlabel=rf"${key}\,\,[TeV/c^2]$",
+    ylabel="Candidates per 0.42 $TeV/c^2$",
+    comparison="pull",
+)
+
+fig.savefig("model_examples_pull.svg", bbox_inches="tight")

plothist/examples/model_ex/model_examples_pull_no_model_unc.py

@@ -0,0 +1,59 @@
+"""
+Pull plot, no model uncertainty
+===============================
+
+Compare data and model with pulls, without model uncertainty.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+from plothist import get_color_palette, make_hist
+
+# Define the histograms
+
+key = "variable_1"
+range = (-9, 12)
+category = "category"
+
+# Define masks
+signal_mask = df[category] == 7
+data_mask = df[category] == 8
+
+background_categories = [0, 1, 2]
+background_categories_labels = [f"c{i}" for i in background_categories]
+background_categories_colors = get_color_palette(
+    "cubehelix", len(background_categories)
+)
+
+background_masks = [df[category] == p for p in background_categories]
+
+# Make histograms
+data_hist = make_hist(df[key][data_mask], bins=50, range=range, weights=1)
+background_hists = [
+    make_hist(df[key][mask], bins=50, range=range, weights=1)
+    for mask in background_masks
+]
+
+# Optional: scale to data
+background_scaling_factor = data_hist.sum().value / sum(background_hists).sum().value
+background_hists = [background_scaling_factor * h for h in background_hists]
+
+###
+from plothist import add_luminosity, plot_data_model_comparison
+
+fig, ax_main, ax_comparison = plot_data_model_comparison(
+    data_hist=data_hist,
+    stacked_components=background_hists,
+    stacked_labels=background_categories_labels,
+    stacked_colors=background_categories_colors,
+    xlabel=rf"${key}\,\,[eV/c^2]$",
+    ylabel=r"Hits in the LMN per $4.2\times 10^{-1}\,\,eV/c^2$",
+    comparison="pull",
+    model_uncertainty=False,  # <--
+)
+
+add_luminosity(collaboration="plothist", ax=ax_main, is_data=False)
+
+fig.savefig("model_examples_pull_no_model_unc.svg", bbox_inches="tight")

plothist/examples/model_ex/model_examples_stacked.py

@@ -0,0 +1,74 @@
+"""
+Data vs model with stacked components
+=====================================
+
+Plot data and a model with stacked components.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+from plothist import get_color_palette, make_hist
+
+# Define the histograms
+
+key = "variable_1"
+range = (-9, 12)
+category = "category"
+
+# Define masks
+signal_mask = df[category] == 7
+data_mask = df[category] == 8
+
+background_categories = [0, 1, 2]
+background_categories_labels = [f"c{i}" for i in background_categories]
+background_categories_colors = get_color_palette(
+    "cubehelix", len(background_categories)
+)
+
+background_masks = [df[category] == p for p in background_categories]
+
+# Make histograms
+data_hist = make_hist(df[key][data_mask], bins=50, range=range, weights=1)
+background_hists = [
+    make_hist(df[key][mask], bins=50, range=range, weights=1)
+    for mask in background_masks
+]
+signal_hist = make_hist(df[key][signal_mask], bins=50, range=range, weights=1)
+
+# Optional: scale to data
+background_scaling_factor = data_hist.sum().value / sum(background_hists).sum().value
+background_hists = [background_scaling_factor * h for h in background_hists]
+
+signal_scaling_factor = data_hist.sum().value / signal_hist.sum().value
+signal_hist *= signal_scaling_factor
+
+###
+from plothist import add_luminosity, plot_data_model_comparison, plot_hist
+
+fig, ax_main, ax_comparison = plot_data_model_comparison(
+    data_hist=data_hist,
+    stacked_components=background_hists,
+    stacked_labels=background_categories_labels,
+    stacked_colors=background_categories_colors,
+    xlabel=key,
+    ylabel="Entries",
+)
+
+# Signal histogram not part of the model and therefore not included in the comparison
+plot_hist(
+    signal_hist,
+    ax=ax_main,
+    color="red",
+    label="Signal",
+    histtype="step",
+)
+
+ax_main.legend()
+
+add_luminosity(
+    collaboration="plothist", ax=ax_main, lumi=3, lumi_unit="zb", preliminary=True
+)
+
+fig.savefig("model_examples_stacked.svg", bbox_inches="tight")

plothist/examples/model_ex/model_examples_stacked_unstacked.py

@@ -0,0 +1,60 @@
+"""
+Data vs model with stacked and unstacked components
+===================================================
+
+Plot data and a model with stacked and unstacked components.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+from plothist import get_color_palette, make_hist
+
+# Define the histograms
+
+key = "variable_1"
+range = (-9, 12)
+category = "category"
+
+# Define masks
+signal_mask = df[category] == 7
+data_mask = df[category] == 8
+
+background_categories = [0, 1, 2]
+background_categories_labels = [f"c{i}" for i in background_categories]
+background_categories_colors = get_color_palette(
+    "cubehelix", len(background_categories)
+)
+
+background_masks = [df[category] == p for p in background_categories]
+
+# Make histograms
+data_hist = make_hist(df[key][data_mask], bins=50, range=range, weights=1)
+background_hists = [
+    make_hist(df[key][mask], bins=50, range=range, weights=1)
+    for mask in background_masks
+]
+
+# Optional: scale to data
+background_scaling_factor = data_hist.sum().value / sum(background_hists).sum().value
+background_hists = [background_scaling_factor * h for h in background_hists]
+
+###
+from plothist import plot_data_model_comparison
+
+fig, ax_main, ax_comparison = plot_data_model_comparison(
+    data_hist=data_hist,
+    stacked_components=background_hists[:2],
+    stacked_labels=background_categories_labels[:2],
+    stacked_colors=background_categories_colors[:2],
+    unstacked_components=background_hists[2:],
+    unstacked_labels=background_categories_labels[2:],
+    unstacked_colors=background_categories_colors[2:],
+    xlabel=key,
+    ylabel="Entries",
+    model_sum_kwargs={"show": True, "label": "Model", "color": "navy"},
+    comparison_ylim=(0.5, 1.5),
+)
+
+fig.savefig("model_examples_stacked_unstacked.svg", bbox_inches="tight")

plothist/examples/model_ex/model_examples_unstacked.py

@@ -0,0 +1,57 @@
+"""
+Data vs model with unstacked components
+=====================================
+
+Plot data and a model with unstacked components.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+from plothist import get_color_palette, make_hist
+
+# Define the histograms
+
+key = "variable_1"
+range = (-9, 12)
+category = "category"
+
+# Define masks
+signal_mask = df[category] == 7
+data_mask = df[category] == 8
+
+background_categories = [0, 1, 2]
+background_categories_labels = [f"c{i}" for i in background_categories]
+background_categories_colors = get_color_palette(
+    "cubehelix", len(background_categories)
+)
+
+background_masks = [df[category] == p for p in background_categories]
+
+# Make histograms
+data_hist = make_hist(df[key][data_mask], bins=50, range=range, weights=1)
+background_hists = [
+    make_hist(df[key][mask], bins=50, range=range, weights=1)
+    for mask in background_masks
+]
+
+# Optional: scale to data
+background_scaling_factor = data_hist.sum().value / sum(background_hists).sum().value
+background_hists = [background_scaling_factor * h for h in background_hists]
+
+###
+from plothist import plot_data_model_comparison
+
+fig, ax_main, ax_comparison = plot_data_model_comparison(
+    data_hist=data_hist,
+    unstacked_components=background_hists,
+    unstacked_labels=background_categories_labels,
+    unstacked_colors=background_categories_colors,
+    xlabel=key,
+    ylabel="Entries",
+    model_sum_kwargs={"label": "Sum(hists)", "color": "navy"},
+    comparison_ylim=[0.5, 1.5],
+)
+
+fig.savefig("model_examples_unstacked.svg", bbox_inches="tight")

plothist/examples/model_ex/model_with_stacked_and_unstacked_function_components.py

@@ -0,0 +1,50 @@
+"""
+Model with stacked and unstacked functional components
+======================================================
+
+Plot a model with stacked and unstacked functional components.
+"""
+
+key = "variable_1"
+range = (-9, 12)
+
+background_categories = [0, 1, 2]
+background_categories_labels = [f"c{i}" for i in background_categories]
+
+
+# Define some random functions that will be used as model components with functions
+from scipy.stats import norm
+
+
+def f_signal(x):
+    return 1000 * norm.pdf(x, loc=0.5, scale=3)
+
+
+def f_background1(x):
+    return 1000 * norm.pdf(x, loc=-1.5, scale=4)
+
+
+def f_background2(x):
+    return 3000 * norm.pdf(x, loc=-1.8, scale=1.8)
+
+
+###
+from plothist import add_text, plot_model
+
+fig, ax = plot_model(
+    stacked_components=[f_background1, f_background2],
+    stacked_labels=background_categories_labels[:2],
+    unstacked_components=[f_signal],
+    unstacked_labels=["Signal"],
+    unstacked_colors=["black"],
+    xlabel=key,
+    ylabel=f"f({key})",
+    model_sum_kwargs={"show": True, "label": "Model", "color": "navy"},
+    function_range=range,
+)
+
+add_text("Model made of functions", ax=ax)
+
+fig.savefig(
+    "model_with_stacked_and_unstacked_function_components.svg", bbox_inches="tight"
+)

plothist/examples/model_ex/model_with_stacked_and_unstacked_histograms_components.py

@@ -0,0 +1,69 @@
+"""
+Model with stacked and unstacked components
+===========================================
+
+Plot a model with stacked and unstacked components.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+from plothist import get_color_palette, make_hist
+
+# Define the histograms
+
+key = "variable_1"
+range = (-9, 12)
+category = "category"
+
+# Define masks
+signal_mask = df[category] == 7
+data_mask = df[category] == 8
+
+background_categories = [0, 1, 2]
+background_categories_labels = [f"c{i}" for i in background_categories]
+background_categories_colors = get_color_palette(
+    "cubehelix", len(background_categories)
+)
+
+background_masks = [df[category] == p for p in background_categories]
+
+# Make histograms
+data_hist = make_hist(df[key][data_mask], bins=50, range=range, weights=1)
+background_hists = [
+    make_hist(df[key][mask], bins=50, range=range, weights=1)
+    for mask in background_masks
+]
+signal_hist = make_hist(df[key][signal_mask], bins=50, range=range, weights=1)
+
+# Optional: scale to data
+background_scaling_factor = data_hist.sum().value / sum(background_hists).sum().value
+background_hists = [background_scaling_factor * h for h in background_hists]
+
+signal_scaling_factor = data_hist.sum().value / signal_hist.sum().value
+signal_hist *= signal_scaling_factor
+
+###
+from plothist import add_text, plot_model
+
+fig, ax = plot_model(
+    stacked_components=background_hists,
+    stacked_labels=background_categories_labels,
+    stacked_colors=background_categories_colors,
+    unstacked_components=[signal_hist],
+    unstacked_labels=["Signal"],
+    unstacked_colors=["black"],
+    unstacked_kwargs_list=[{"linestyle": "dotted"}],
+    xlabel=key,
+    ylabel="Entries",
+    model_sum_kwargs={"show": True, "label": "Model", "color": "navy"},
+    model_uncertainty_label="Stat. unc.",
+)
+
+add_text("Model made of histograms", ax=ax)
+
+fig.savefig(
+    "model_with_stacked_and_unstacked_histograms_components.svg",
+    bbox_inches="tight",
+)

plothist/examples/model_ex/ratio_data_vs_model_with_stacked_and_unstacked_function_components.py

@@ -0,0 +1,61 @@
+"""
+Data vs functional model
+========================
+
+Compare data and model with stacked and unstacked functional components.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+from plothist import make_hist
+
+# Define the histograms
+
+key = "variable_1"
+range = (-9, 12)
+category = "category"
+
+# Define masks
+data_mask = df[category] == 8
+
+# Make histograms
+data_hist = make_hist(df[key][data_mask], bins=50, range=range, weights=1)
+
+# Define some random functions that will be used as model components with functions
+from scipy.stats import norm
+
+
+def f_signal(x):
+    return 1000 * norm.pdf(x, loc=0.5, scale=3)
+
+
+def f_background1(x):
+    return 1000 * norm.pdf(x, loc=-1.5, scale=4)
+
+
+def f_background2(x):
+    return 3000 * norm.pdf(x, loc=-1.8, scale=1.8)
+
+
+###
+from plothist import plot_data_model_comparison
+
+fig, ax_main, ax_comparison = plot_data_model_comparison(
+    data_hist=data_hist,
+    stacked_components=[f_background1, f_background2],
+    stacked_labels=["c0", "c1"],
+    unstacked_components=[f_signal],
+    unstacked_labels=["Signal"],
+    unstacked_colors=["#8EBA42"],
+    xlabel=key,
+    ylabel="Entries",
+    model_sum_kwargs={"show": True, "label": "Model", "color": "navy"},
+    comparison="pull",
+)
+
+fig.savefig(
+    "ratio_data_vs_model_with_stacked_and_unstacked_function_components.svg",
+    bbox_inches="tight",
+)

plothist/examples/utility/README.rst

@@ -0,0 +1,4 @@
+Utilities
+---------
+
+Gallery of images that are used in the utility section.

plothist/examples/utility/add_text_example.py

@@ -0,0 +1,39 @@
+"""
+Add text
+========
+
+Examples of use of ``add_text()``.
+"""
+
+###
+import matplotlib.pyplot as plt
+
+from plothist import add_text
+
+fig, ax = plt.subplots()
+
+positions = [
+    ("right_in", "top_in"),
+    ("left_in", "top_in"),
+    ("left_in", "bottom_in"),
+    ("right_in", "bottom_in"),
+    ("right", "top_out"),
+    ("left", "top_out"),
+    ("right_out", "top_in"),
+    ("right_out", "bottom_in"),
+    ("right", "bottom_out"),
+    ("left", "bottom_out"),
+]
+
+for x, y in positions:
+    x_label = x.replace("_", r"\_")
+    y_label = y.replace("_", r"\_")
+    add_text(
+        f"$\\mathtt{{add\\_text()}}$\n"
+        f'$\\mathtt{{x = }}$"$\\mathtt{{{x_label}}}$"\n'
+        f'$\\mathtt{{y = }}$"$\\mathtt{{{y_label}}}$"',
+        x=x,
+        y=y,
+    )
+
+fig.savefig("add_text_example.svg", bbox_inches="tight")