plothist 1.4.0__py3-none-any.whl → 1.5.0__py3-none-any.whl

plothist/examples/1d_hist/1d_comparison_split_ratio.py

@@ -0,0 +1,37 @@
+"""
+Ratio, split errors
+===================
+
+Compare two 1D histograms using the ratio [h1/h2] method and split the errors.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+name = "variable_1"
+
+x1 = df[name][df["category"] == 2]
+x2 = df[name][df["category"] == 3]
+
+x_range = (min(*x1, *x2), max(*x1, *x2))
+
+from plothist import make_hist
+
+h1 = make_hist(x1, bins=50, range=x_range)
+h2 = make_hist(x2, bins=50, range=x_range)
+
+###
+from plothist import plot_two_hist_comparison
+
+fig, ax_main, ax_comparison = plot_two_hist_comparison(
+    h1,
+    h2,
+    xlabel=name,
+    ylabel="Entries",
+    h1_label=r"$\mathbf{h1}$",
+    h2_label=r"$\mathbf{h2}$",
+    comparison="split_ratio",
+)
+
+fig.savefig("1d_comparison_split_ratio.svg", bbox_inches="tight")

plothist/examples/1d_hist/1d_elt1.py

@@ -0,0 +1,38 @@
+"""
+Multiple histograms
+===================
+
+Plot multiple histograms on the same plot using ``plot_hist()``.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+###
+import matplotlib.pyplot as plt
+
+from plothist import make_hist, plot_hist
+
+name = "variable_1"
+category = "category"
+
+x1 = df[name][df[category] == 1]
+x2 = df[name][df[category] == 2]
+
+x_range = (min(*x1, *x2), max(*x1, *x2))
+
+h1 = make_hist(x1, bins=50, range=x_range)
+h2 = make_hist(x2, bins=50, range=x_range)
+
+fig, ax = plt.subplots()
+
+plot_hist(h1, ax=ax, histtype="step", linewidth=1.2, label="c1")
+plot_hist(h2, ax=ax, histtype="step", linewidth=1.2, label="c2")
+
+ax.set_xlabel(name)
+ax.set_ylabel("Entries")
+ax.set_xlim(x_range)
+ax.legend()
+
+fig.savefig("1d_elt1.svg", bbox_inches="tight")

plothist/examples/1d_hist/1d_elt1_stacked.py

@@ -0,0 +1,45 @@
+"""
+Stack histograms
+================
+
+Stack two 1D histograms with ``plot_hist()``.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+import matplotlib.pyplot as plt
+
+from plothist import make_hist, plot_hist
+
+name = "variable_1"
+category = "category"
+
+x1 = df[name][df[category] == 1]
+x2 = df[name][df[category] == 2]
+
+x_range = (min(*x1, *x2), max(*x1, *x2))
+
+h1 = make_hist(x1, bins=50, range=x_range)
+h2 = make_hist(x2, bins=50, range=x_range)
+
+###
+fig, ax = plt.subplots()
+
+plot_hist(
+    [h1, h2],
+    label=["c1", "c2"],
+    ax=ax,
+    edgecolor="black",
+    linewidth=0.5,
+    histtype="stepfilled",
+    stacked=True,
+)
+
+ax.set_xlabel(name)
+ax.set_ylabel("Entries")
+ax.set_xlim(x_range)
+ax.legend()
+
+fig.savefig("1d_elt1_stacked.svg", bbox_inches="tight")

plothist/examples/1d_hist/1d_elt2.py

@@ -0,0 +1,33 @@
+"""
+Histogram with uncertainties
+============================
+
+Plot a 1D histogram with error bars using ``plot_error_hist()``.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+###
+import matplotlib.pyplot as plt
+
+from plothist import make_hist, plot_error_hist
+
+name = "variable_1"
+category = "category"
+
+x1 = df[name][df[category] == 3]
+
+h1 = make_hist(x1)
+
+fig, ax = plt.subplots()
+
+plot_error_hist(h1, ax=ax, color="black", label="$h1_{err}$")
+
+ax.set_xlabel(name)
+ax.set_ylabel("Entries")
+ax.set_ylim(ymin=0)
+ax.legend()
+
+fig.savefig("1d_elt2.svg", bbox_inches="tight")

plothist/examples/1d_hist/1d_hist_simple.py

@@ -0,0 +1,28 @@
+"""
+Histogram
+=========
+
+Plot a 1D histogram with ``plot_hist()``.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+###
+import matplotlib.pyplot as plt
+
+from plothist import make_hist, plot_hist
+
+name = "variable_0"
+
+fig, ax = plt.subplots()
+
+h = make_hist(df[name])
+
+plot_hist(h, ax=ax)
+
+ax.set_xlabel(name)
+ax.set_ylabel("Entries")
+
+fig.savefig("1d_hist_simple.svg", bbox_inches="tight")

plothist/examples/1d_hist/1d_int_category.py

@@ -0,0 +1,41 @@
+"""
+Integer categories
+==================
+
+Plot a 1D histogram with integer categories.
+"""
+
+###
+import boost_histogram as bh
+import matplotlib.pyplot as plt
+
+from plothist import plot_hist
+
+# 3 integer categories
+int_categories = [-10, 5, 72]
+
+# Integer category axis with 3 bins
+axis = bh.axis.IntCategory(categories=int_categories)
+
+# 6 data points,
+data = [-10, -10, 5, 72, 72, 72]
+
+# Create and fill the histogram
+h = bh.Histogram(axis, storage=bh.storage.Weight())
+h.fill(data)
+
+# Plot the histogram
+fig, ax = plt.subplots()
+
+plot_hist(h, ax=ax)
+
+# Set the x-ticks to the middle of the bins and label them
+ax.set_xticks([i + 0.5 for i in range(len(int_categories))])
+ax.set_xticklabels(int_categories)
+ax.minorticks_off()
+
+ax.set_xlabel("Integer Category")
+ax.set_ylabel("Entries")
+ax.set_xlim(0, len(int_categories))
+
+fig.savefig("1d_int_category.svg", bbox_inches="tight")

plothist/examples/1d_hist/1d_profile.py

@@ -0,0 +1,33 @@
+"""
+Mean histogram (profile)
+========================
+
+Plot a 1D mean histogram (profile).
+"""
+
+###
+import boost_histogram as bh
+import matplotlib.pyplot as plt
+
+from plothist import plot_error_hist
+
+# Regular axis with 3 bins from -1 to 1
+axis = bh.axis.Regular(3, -1, 1)
+
+# 6 data points, two in each bin
+data = [-0.5, -0.5, 0.0, 0.0, 0.5, 0.5]
+sample = [0, 100, 40, 60, 0, 20]
+weights = [1, 1, 1, 1, 1, 1]
+
+h = bh.Histogram(axis, storage=bh.storage.WeightedMean())
+h.fill(data, weight=weights, sample=sample)
+
+fig, ax = plt.subplots()
+
+plot_error_hist(h, ax=ax)
+
+ax.set_xlabel("Variable")
+ax.set_ylabel("Mean")
+ax.set_xlim(-1, 1)
+
+fig.savefig("1d_profile.svg", bbox_inches="tight")

plothist/examples/1d_hist/1d_side_by_side.py

@@ -0,0 +1,58 @@
+"""
+Side-by-side categories
+=======================
+
+Plot multiple 1D histograms with categories side by side.
+"""
+
+###
+import boost_histogram as bh
+import matplotlib.pyplot as plt
+import numpy as np
+
+from plothist import plot_hist
+
+rng = np.random.default_rng(8311311)
+
+# String categories
+categories = ["A", "B", "C"]
+
+# Axis with the 3 bins
+axis = bh.axis.StrCategory(categories=categories)
+
+## Works also with integers
+# categories = [-5, 10, 137]
+# axis = bh.axis.IntCategory(categories=categories)
+
+# Generate data for 3 histograms
+data = [
+    rng.choice(categories, 20),
+    rng.choice(categories, 30),
+    rng.choice(categories, 40),
+]
+
+# Create and fill the histograms
+histos = [bh.Histogram(axis, storage=bh.storage.Weight()) for _ in range(len(data))]
+histos = [histo.fill(data[i]) for i, histo in enumerate(histos)]
+
+labels = [f"$h_{{{i}}}$" for i in range(len(histos))]
+
+# Plot the histogram
+fig, ax = plt.subplots()
+
+# Use a specificity of matplotlib: when a list of histograms is given, it will plot them side by side unless stacked=True or histtype is a "step" type.
+plot_hist(histos, ax=ax, label=labels)
+
+# Set the x-ticks to the middle of the bins and label them
+ax.set_xlim(0, len(categories))
+ax.set_xticks([i + 0.5 for i in range(len(categories))])
+ax.set_xticklabels(categories)
+ax.minorticks_off()
+# Get nice looking y-axis ticks
+ax.set_ylim(top=int(np.max([np.max(histo.values()) for histo in histos]) * 1.5))
+
+ax.set_xlabel("Category")
+ax.set_ylabel("Entries")
+ax.legend()
+
+fig.savefig("1d_side_by_side.svg", bbox_inches="tight")

plothist/examples/1d_hist/1d_str_category.py

@@ -0,0 +1,41 @@
+"""
+String categories
+=================
+
+Plot a 1D histogram with string categories.
+"""
+
+###
+import boost_histogram as bh
+import matplotlib.pyplot as plt
+
+from plothist import plot_hist
+
+# 3 str categories
+str_categories = ["a", "b", "c"]
+
+# String category axis with 3 bins
+axis = bh.axis.StrCategory(categories=str_categories)
+
+# 6 data points,
+data = ["a", "a", "a", "b", "b", "c"]
+
+# Create and fill the histogram
+h = bh.Histogram(axis, storage=bh.storage.Weight())
+h.fill(data)
+
+# Plot the histogram
+fig, ax = plt.subplots()
+
+plot_hist(h, ax=ax)
+
+# Set the x-ticks to the middle of the bins and label them
+ax.set_xticks([i + 0.5 for i in range(len(str_categories))])
+ax.set_xticklabels(str_categories)
+ax.minorticks_off()
+
+ax.set_xlabel("String Category")
+ax.set_ylabel("Entries")
+ax.set_xlim(0, len(str_categories))
+
+fig.savefig("1d_str_category.svg", bbox_inches="tight")

plothist/examples/1d_hist/README.rst

@@ -0,0 +1,4 @@
+Plot 1D histograms
+------------------
+
+Gallery of images that are used in the 1D histogram section.

plothist/examples/2d_hist/2d_hist_correlations.py

@@ -0,0 +1,65 @@
+"""
+2D histograms
+=============
+
+Plot multiple 2D histograms with the variable registry.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+
+###
+import os
+import time
+from itertools import combinations
+
+from plothist import (
+    create_variable_registry,
+    get_variable_from_registry,
+    make_2d_hist,
+    plot_2d_hist,
+    update_variable_registry_ranges,
+)
+
+# No need to redo this step if the registry was already created before
+variable_keys = ["variable_0", "variable_1", "variable_2"]
+unique_id = str(int(time.time() * 1000))[-8:]  # unique ID based on current time
+temporary_registry_path = f"./_temporary_variable_registry_{unique_id}.yaml"
+create_variable_registry(variable_keys, path=temporary_registry_path)
+update_variable_registry_ranges(df, variable_keys, path=temporary_registry_path)
+
+# Get all the correlation plot between the variables
+variable_keys_combinations = list(combinations(variable_keys, 2))
+
+figs = []
+
+for variable_keys_combination in variable_keys_combinations:
+    variable0 = get_variable_from_registry(
+        variable_keys_combination[0], path=temporary_registry_path
+    )
+    variable1 = get_variable_from_registry(
+        variable_keys_combination[1], path=temporary_registry_path
+    )
+
+    h = make_2d_hist(
+        [df[variable0["name"]], df[variable1["name"]]],
+        bins=(variable0["bins"], variable1["bins"]),
+        range=(variable0["range"], variable1["range"]),
+    )
+
+    fig, ax, ax_colorbar = plot_2d_hist(h, colorbar_kwargs={"label": "Entries"})
+
+    ax.set_xlabel(variable0["name"])
+    ax.set_ylabel(variable1["name"])
+
+    ax.set_xlim(variable0["range"])
+    ax.set_ylim(variable1["range"])
+
+    figs.append(fig)
+
+for i, fig in enumerate(figs):
+    fig.savefig(f"2d_hist_correlations_{i}.svg", bbox_inches="tight")
+
+os.remove(temporary_registry_path)

plothist/examples/2d_hist/2d_hist_simple.py

@@ -0,0 +1,28 @@
+"""
+2D histogram
+============
+
+Plot a 2D histogram with ``plot_2d_hist()``.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+###
+from plothist import make_2d_hist, plot_2d_hist
+
+name_x = "variable_0"
+name_y = "variable_1"
+
+h = make_2d_hist([df[name_x], df[name_y]], bins=[10, 10])
+
+fig, ax, ax_colorbar = plot_2d_hist(h, colorbar_kwargs={"label": "Entries"})
+
+ax.set_xlabel(name_x)
+ax.set_ylabel(name_y)
+
+ax.set_xlim(-9, 9)
+ax.set_ylim(-9, 9)
+
+fig.savefig("2d_hist_simple.svg", bbox_inches="tight")

plothist/examples/2d_hist/2d_hist_simple_discrete_colormap.py

@@ -0,0 +1,42 @@
+"""
+2D histogram, discrete colormap
+===============================
+
+Plot a 2D histogram with ``plot_2d_hist()`` with a discrete colormap.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+from plothist import make_2d_hist, plot_2d_hist
+
+name_x = "variable_0"
+name_y = "variable_1"
+
+# We only take a subset of the data
+nentries = 1000
+
+h = make_2d_hist([df[name_x][:nentries], df[name_y][:nentries]])
+
+###
+from matplotlib.colors import ListedColormap
+
+from plothist import get_color_palette
+
+# 0 entries will be white, the rest will have one color from the plasma colormap per entry value
+cmap = ListedColormap(
+    ["white", *list(get_color_palette("plasma", int(h.values().max()) * 2 - 1))]
+)
+
+fig, ax, ax_colorbar = plot_2d_hist(
+    h, colorbar_kwargs={"label": "Entries"}, pcolormesh_kwargs={"cmap": cmap}
+)
+
+ax.set_xlabel(name_x)
+ax.set_ylabel(name_y)
+
+ax.set_xlim(-4.5, 4.5)
+ax.set_ylim(-4.5, 4.5)
+
+fig.savefig("2d_hist_simple_discrete_colormap.svg", bbox_inches="tight")

plothist/examples/2d_hist/2d_hist_uneven.py

@@ -0,0 +1,28 @@
+"""
+2D histogram, uneven binning
+============================
+
+Plot a 2D histogram with uneven binning.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+###
+from plothist import make_2d_hist, plot_2d_hist
+
+name_x = "variable_0"
+name_y = "variable_1"
+# Bins [-10,0], [0,10] for variable 1,
+# and bins [-10,-5], [-5,0], [0,5], [5,10] for variable 2
+bins = [[-10, 0, 10], [-10, -5, 0, 5, 10]]
+
+h = make_2d_hist([df[name_x], df[name_y]], bins=bins)
+
+fig, ax, ax_colorbar = plot_2d_hist(h, colorbar_kwargs={"label": "Entries"})
+
+ax.set_xlabel(name_x)
+ax.set_ylabel(name_y)
+
+fig.savefig("2d_hist_uneven.svg", bbox_inches="tight")

plothist/examples/2d_hist/2d_hist_with_projections.py

@@ -0,0 +1,36 @@
+"""
+2D histogram with projections
+==============================
+
+Plot a 2D histogram with the two 1D projections.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+###
+from plothist import make_2d_hist, plot_2d_hist_with_projections
+
+name_x = "variable_0"
+name_y = "variable_1"
+
+h = make_2d_hist([df[name_x], df[name_y]])
+
+(
+    fig,
+    ax_2d,
+    ax_x_projection,
+    ax_y_projection,
+    ax_colorbar,
+) = plot_2d_hist_with_projections(
+    h,
+    xlabel="variable_0",
+    ylabel="variable_1",
+    ylabel_x_projection="Entries",
+    xlabel_y_projection="Entries",
+    offset_x_labels=False,
+    colorbar_kwargs={"label": "Entries"},
+)
+
+fig.savefig("2d_hist_with_projections.svg", bbox_inches="tight")

plothist/examples/2d_hist/README.rst

@@ -0,0 +1,4 @@
+Plot 2D histograms
+------------------
+
+Gallery of images that are used in the section about plotting 2D histograms.

plothist/examples/README.rst

@@ -0,0 +1,7 @@
+Example gallery
+===============
+
+Gallery of images that are used in the doc.
+
+.. note::
+   Click on an image to see the source code that generates it.

plothist/examples/advanced/1d_comparison_advanced.py

@@ -0,0 +1,87 @@
+"""
+Multiple comparisons
+====================
+
+Compare two 1D histograms using the pull and ratio methods on the same plot.
+"""
+
+from plothist_utils import get_dummy_data
+
+df = get_dummy_data()
+
+###
+from plothist import (
+    create_comparison_figure,
+    get_color_palette,
+    make_hist,
+    plot_comparison,
+    plot_error_hist,
+    plot_hist,
+)
+
+name = "variable_1"
+category = "category"
+
+x1 = df[name][df[category] == 1]
+x2 = df[name][df[category] == 4]
+x3 = df[name][df[category] == 3]
+x4 = df[name][df[category] == 5]
+
+x_range = (-9, 9)
+
+h1 = make_hist(x3, bins=50, range=x_range)
+h2 = make_hist(x4, bins=50, range=x_range)
+h3 = make_hist(x1, bins=50, range=x_range)
+h4 = make_hist(x2, bins=50, range=x_range)
+
+# Create the 3 axes that we need for this plot
+fig, axes = create_comparison_figure(
+    figsize=(6, 6), nrows=3, gridspec_kw={"height_ratios": [5, 1, 1]}
+)
+
+# Assign each axes: 1 to plot the histograms and 2 for the comparison plots
+ax_main, ax1_comparison, ax2_comparison = axes
+
+# Get the red and the blue from the default color cycle
+colors = get_color_palette("ggplot", 2)
+
+# Here, we use step as a histtype to only draw the line
+plot_hist(h1, label="Train A", ax=ax_main, histtype="step", linewidth=1.2, density=True)
+plot_hist(h3, label="Train B", ax=ax_main, histtype="step", linewidth=1.2, density=True)
+# And then, to make the plot easier to read, we redraw them with stepfilled, which add color below the line
+plot_hist(
+    h1, ax=ax_main, histtype="stepfilled", color=colors[0], alpha=0.2, density=True
+)
+plot_hist(
+    h3, ax=ax_main, histtype="stepfilled", color=colors[1], alpha=0.2, density=True
+)
+
+# We plot 2 additional histograms with point style
+plot_error_hist(h2, label="Test A", ax=ax_main, color="blue", density=True)
+plot_error_hist(h4, label="Test B", ax=ax_main, color="red", density=True)
+
+# First comparison is using pulls. We also change the color of the bars to make the plot easier to read
+plot_comparison(
+    h2, h1, ax=ax1_comparison, comparison="pull", color=colors[0], alpha=0.7
+)
+# Second comparison is using the default "ratio". Same strategy as pulls
+plot_comparison(h4, h3, ax=ax2_comparison, color=colors[1], alpha=0.7)
+
+# Harmonize the range of each axes
+ax_main.set_xlim(x_range)
+ax1_comparison.set_xlim(x_range)
+ax2_comparison.set_xlim(x_range)
+
+# Set the labels for the different axes
+ax_main.set_ylabel("Entry density")
+ax1_comparison.set_ylabel("$Pull_{A}$")
+ax2_comparison.set_ylabel("$Ratio_{B}$")
+ax2_comparison.set_xlabel("Variable [unit]")
+
+# Add the legend
+ax_main.legend(loc="upper left")
+
+# Align the ylabels
+fig.align_ylabels()
+
+fig.savefig("1d_comparison_advanced.svg", bbox_inches="tight")