.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "auto_examples/applications/plot_prediction_latency.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code. or to run this example in your browser via Binder .. rst-class:: sphx-glr-example-title .. _sphx_glr_auto_examples_applications_plot_prediction_latency.py: ================== 预测延迟 ================== 这是一个展示各种scikit-learn估计器预测延迟的示例。 目标是测量在批量或原子（即一个接一个）模式下进行预测时可以预期的延迟。 图表以箱线图的形式表示预测延迟的分布。 .. GENERATED FROM PYTHON SOURCE LINES 13-38 .. code-block:: Python # 作者：scikit-learn 开发者 # SPDX许可证标识符：BSD-3-Clause import gc import time from collections import defaultdict import matplotlib.pyplot as plt import numpy as np from sklearn.datasets import make_regression from sklearn.ensemble import RandomForestRegressor from sklearn.linear_model import Ridge, SGDRegressor from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.svm import SVR from sklearn.utils import shuffle def _not_in_sphinx(): # 检测我们是否由sphinx构建器运行的黑客方法 return "__file__" in globals() .. GENERATED FROM PYTHON SOURCE LINES 39-41 基准测试和绘图辅助函数 ----------------------------------- .. GENERATED FROM PYTHON SOURCE LINES 41-287 .. code-block:: Python def atomic_benchmark_estimator(estimator, X_test, verbose=False): """测量每个实例的运行时间预测。""" n_instances = X_test.shape[0] runtimes = np.zeros(n_instances, dtype=float) for i in range(n_instances): instance = X_test[[i], :] start = time.time() estimator.predict(instance) runtimes[i] = time.time() - start if verbose: print( "atomic_benchmark runtimes:", min(runtimes), np.percentile(runtimes, 50), max(runtimes), ) return runtimes def bulk_benchmark_estimator(estimator, X_test, n_bulk_repeats, verbose): """测量整个输入的运行时间预测。""" n_instances = X_test.shape[0] runtimes = np.zeros(n_bulk_repeats, dtype=float) for i in range(n_bulk_repeats): start = time.time() estimator.predict(X_test) runtimes[i] = time.time() - start runtimes = np.array(list(map(lambda x: x / float(n_instances), runtimes))) if verbose: print( "bulk_benchmark runtimes:", min(runtimes), np.percentile(runtimes, 50), max(runtimes), ) return runtimes def benchmark_estimator(estimator, X_test, n_bulk_repeats=30, verbose=False): """测量预测在原子模式和批量模式下的运行时间。 Parameters ---------- estimator : 已经训练好的支持 `predict()` 的估计器 X_test : 测试输入 n_bulk_repeats : 评估批量模式时重复的次数 Returns ------- atomic_runtimes, bulk_runtimes : 一对 `np.array` ，包含以秒为单位的运行时间。 """ atomic_runtimes = atomic_benchmark_estimator(estimator, X_test, verbose) bulk_runtimes = bulk_benchmark_estimator(estimator, X_test, n_bulk_repeats, verbose) return atomic_runtimes, bulk_runtimes def generate_dataset(n_train, n_test, n_features, noise=0.1, verbose=False): """生成具有给定参数的回归数据集。""" if verbose: print("generating dataset...") X, y, coef = make_regression( n_samples=n_train + n_test, n_features=n_features, noise=noise, coef=True ) random_seed = 13 X_train, X_test, y_train, y_test = train_test_split( X, y, train_size=n_train, test_size=n_test, random_state=random_seed ) X_train, y_train = shuffle(X_train, y_train, random_state=random_seed) X_scaler = StandardScaler() X_train = X_scaler.fit_transform(X_train) X_test = X_scaler.transform(X_test) y_scaler = StandardScaler() y_train = y_scaler.fit_transform(y_train[:, None])[:, 0] y_test = y_scaler.transform(y_test[:, None])[:, 0] gc.collect() if verbose: print("ok") return X_train, y_train, X_test, y_test def boxplot_runtimes(runtimes, pred_type, configuration): """绘制一个包含预测运行时间箱线图的新 `Figure` 。 Parameters ---------- runtimes : 以微秒为单位的延迟 `np.array` 列表 cls_names : 生成运行时间的估计器类名列表 pred_type : 'bulk' 或 'atomic' """ fig, ax1 = plt.subplots(figsize=(10, 6)) bp = plt.boxplot( runtimes, ) cls_infos = [ "%s\n(%d %s)" % ( estimator_conf["name"], estimator_conf["complexity_computer"](estimator_conf["instance"]), estimator_conf["complexity_label"], ) for estimator_conf in configuration["estimators"] ] plt.setp(ax1, xticklabels=cls_infos) plt.setp(bp["boxes"], color="black") plt.setp(bp["whiskers"], color="black") plt.setp(bp["fliers"], color="red", marker="+") ax1.yaxis.grid(True, linestyle="-", which="major", color="lightgrey", alpha=0.5) ax1.set_axisbelow(True) ax1.set_title( "Prediction Time per Instance - %s, %d feats." % (pred_type.capitalize(), configuration["n_features"]) ) ax1.set_ylabel("Prediction Time (us)") plt.show() def benchmark(configuration): """运行整个基准测试。""" X_train, y_train, X_test, y_test = generate_dataset( configuration["n_train"], configuration["n_test"], configuration["n_features"] ) stats = {} for estimator_conf in configuration["estimators"]: print("Benchmarking", estimator_conf["instance"]) estimator_conf["instance"].fit(X_train, y_train) gc.collect() a, b = benchmark_estimator(estimator_conf["instance"], X_test) stats[estimator_conf["name"]] = {"atomic": a, "bulk": b} cls_names = [ estimator_conf["name"] for estimator_conf in configuration["estimators"] ] runtimes = [1e6 * stats[clf_name]["atomic"] for clf_name in cls_names] boxplot_runtimes(runtimes, "atomic", configuration) runtimes = [1e6 * stats[clf_name]["bulk"] for clf_name in cls_names] boxplot_runtimes(runtimes, "bulk (%d)" % configuration["n_test"], configuration) def n_feature_influence(estimators, n_train, n_test, n_features, percentile): """估计特征数量对预测时间的影响。 Parameters ---------- estimators : 用于基准测试的（名称（str），估计器）字典 n_train : 训练实例的数量（int） n_test : 测试实例的数量（int） n_features : 要测试的特征空间维度列表（int） percentile : 测量速度的百分位数（int [0-100]） Returns: -------- percentiles : 字典（估计器名称， 字典（特征数量，百分位性能（微秒））） """ percentiles = defaultdict(defaultdict) for n in n_features: print("benchmarking with %d features" % n) X_train, y_train, X_test, y_test = generate_dataset(n_train, n_test, n) for cls_name, estimator in estimators.items(): estimator.fit(X_train, y_train) gc.collect() runtimes = bulk_benchmark_estimator(estimator, X_test, 30, False) percentiles[cls_name][n] = 1e6 * np.percentile(runtimes, percentile) return percentiles def plot_n_features_influence(percentiles, percentile): fig, ax1 = plt.subplots(figsize=(10, 6)) colors = ["r", "g", "b"] for i, cls_name in enumerate(percentiles.keys()): x = np.array(sorted(percentiles[cls_name].keys())) y = np.array([percentiles[cls_name][n] for n in x]) plt.plot( x, y, color=colors[i], ) ax1.yaxis.grid(True, linestyle="-", which="major", color="lightgrey", alpha=0.5) ax1.set_axisbelow(True) ax1.set_title("Evolution of Prediction Time with #Features") ax1.set_xlabel("#Features") ax1.set_ylabel("Prediction Time at %d%%-ile (us)" % percentile) plt.show() def benchmark_throughputs(configuration, duration_secs=0.1): """不同估计器的基准吞吐量。""" X_train, y_train, X_test, y_test = generate_dataset( configuration["n_train"], configuration["n_test"], configuration["n_features"] ) throughputs = dict() for estimator_config in configuration["estimators"]: estimator_config["instance"].fit(X_train, y_train) start_time = time.time() n_predictions = 0 while (time.time() - start_time) < duration_secs: estimator_config["instance"].predict(X_test[[0]]) n_predictions += 1 throughputs[estimator_config["name"]] = n_predictions / duration_secs return throughputs def plot_benchmark_throughput(throughputs, configuration): fig, ax = plt.subplots(figsize=(10, 6)) colors = ["r", "g", "b"] cls_infos = [ "%s\n(%d %s)" % ( estimator_conf["name"], estimator_conf["complexity_computer"](estimator_conf["instance"]), estimator_conf["complexity_label"], ) for estimator_conf in configuration["estimators"] ] cls_values = [ throughputs[estimator_conf["name"]] for estimator_conf in configuration["estimators"] ] plt.bar(range(len(throughputs)), cls_values, width=0.5, color=colors) ax.set_xticks(np.linspace(0.25, len(throughputs) - 0.75, len(throughputs))) ax.set_xticklabels(cls_infos, fontsize=10) ymax = max(cls_values) * 1.2 ax.set_ylim((0, ymax)) ax.set_ylabel("Throughput (predictions/sec)") ax.set_title( "Prediction Throughput for different estimators (%d features)" % configuration["n_features"] ) plt.show() .. GENERATED FROM PYTHON SOURCE LINES 288-290 基准测试各种回归器的大量/原子预测速度 ------------------------------------------------------------- .. GENERATED FROM PYTHON SOURCE LINES 290-320 .. code-block:: Python configuration = { "n_train": int(1e3), "n_test": int(1e2), "n_features": int(1e2), "estimators": [ { "name": "Linear Model", "instance": SGDRegressor( penalty="elasticnet", alpha=0.01, l1_ratio=0.25, tol=1e-4 ), "complexity_label": "non-zero coefficients", "complexity_computer": lambda clf: np.count_nonzero(clf.coef_), }, { "name": "RandomForest", "instance": RandomForestRegressor(), "complexity_label": "estimators", "complexity_computer": lambda clf: clf.n_estimators, }, { "name": "SVR", "instance": SVR(kernel="rbf"), "complexity_label": "support vectors", "complexity_computer": lambda clf: len(clf.support_vectors_), }, ], } benchmark(configuration) .. rst-class:: sphx-glr-horizontal * .. image-sg:: /auto_examples/applications/images/sphx_glr_plot_prediction_latency_001.png :alt: Prediction Time per Instance - Atomic, 100 feats. :srcset: /auto_examples/applications/images/sphx_glr_plot_prediction_latency_001.png :class: sphx-glr-multi-img * .. image-sg:: /auto_examples/applications/images/sphx_glr_plot_prediction_latency_002.png :alt: Prediction Time per Instance - Bulk (100), 100 feats. :srcset: /auto_examples/applications/images/sphx_glr_plot_prediction_latency_002.png :class: sphx-glr-multi-img .. rst-class:: sphx-glr-script-out .. code-block:: none Benchmarking SGDRegressor(alpha=0.01, l1_ratio=0.25, penalty='elasticnet', tol=0.0001) Benchmarking RandomForestRegressor() Benchmarking SVR() .. GENERATED FROM PYTHON SOURCE LINES 321-323 基准测试 n_features 对预测速度的影响 -------------------------------------------------- .. GENERATED FROM PYTHON SOURCE LINES 323-334 .. code-block:: Python percentile = 90 percentiles = n_feature_influence( {"ridge": Ridge()}, configuration["n_train"], configuration["n_test"], [100, 250, 500], percentile, ) plot_n_features_influence(percentiles, percentile) .. image-sg:: /auto_examples/applications/images/sphx_glr_plot_prediction_latency_003.png :alt: Evolution of Prediction Time with #Features :srcset: /auto_examples/applications/images/sphx_glr_plot_prediction_latency_003.png :class: sphx-glr-single-img .. rst-class:: sphx-glr-script-out .. code-block:: none benchmarking with 100 features benchmarking with 250 features benchmarking with 500 features .. GENERATED FROM PYTHON SOURCE LINES 335-337 基准吞吐量 -------------------- .. GENERATED FROM PYTHON SOURCE LINES 337-341 .. code-block:: Python throughputs = benchmark_throughputs(configuration) plot_benchmark_throughput(throughputs, configuration) .. image-sg:: /auto_examples/applications/images/sphx_glr_plot_prediction_latency_004.png :alt: Prediction Throughput for different estimators (100 features) :srcset: /auto_examples/applications/images/sphx_glr_plot_prediction_latency_004.png :class: sphx-glr-single-img .. rst-class:: sphx-glr-timing **Total running time of the script:** (0 minutes 28.432 seconds) .. _sphx_glr_download_auto_examples_applications_plot_prediction_latency.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: binder-badge .. image:: images/binder_badge_logo.svg :target: https://mybinder.org/v2/gh/scikit-learn/scikit-learn/main?urlpath=lab/tree/notebooks/auto_examples/applications/plot_prediction_latency.ipynb :alt: Launch binder :width: 150 px .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: plot_prediction_latency.ipynb ` .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: plot_prediction_latency.py ` .. container:: sphx-glr-download sphx-glr-download-zip :download:`Download zipped: plot_prediction_latency.zip ` .. include:: plot_prediction_latency.recommendations .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_