Benchmark of PolynomialFeatures + partialfit of SGDClassifier (standalone)

This benchmark looks into a new implementation of PolynomialFeatures proposed in PR13290. It tests the following configurations:

This script is standalone and does not require pymlbenchmark as opposed to Benchmark of PolynomialFeatures + partialfit of SGDClassifier which reuse functions implemented in pymlbenchmark.

from time import perf_counter as time
import numpy
import numpy as np
from numpy.random import rand
import matplotlib.pyplot as plt
import pandas
import sklearn
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import SGDClassifier
try:
    from sklearn.utils._testing import ignore_warnings
except ImportError:
    from sklearn.utils.testing import ignore_warnings
from mlinsights.mlmodel import ExtendedFeatures

Implementations to benchmark

def fcts_model(X, y):

    model1 = SGDClassifier()
    model2 = make_pipeline(PolynomialFeatures(), SGDClassifier())
    model3 = make_pipeline(ExtendedFeatures(kind='poly'), SGDClassifier())
    model4 = make_pipeline(ExtendedFeatures(kind='poly-slow'), SGDClassifier())

    model1.fit(PolynomialFeatures().fit_transform(X), y)
    model2.fit(X, y)
    model3.fit(X, y)
    model4.fit(X, y)

    def partial_fit_model1(X, y, model=model1):
        return model.partial_fit(X, y)

    def partial_fit_model2(X, y, model=model2):
        X2 = model.steps[0][1].transform(X)
        return model.steps[1][1].partial_fit(X2, y)

    def partial_fit_model3(X, y, model=model3):
        X2 = model.steps[0][1].transform(X)
        return model.steps[1][1].partial_fit(X2, y)

    def partial_fit_model4(X, y, model=model4):
        X2 = model.steps[0][1].transform(X)
        return model.steps[1][1].partial_fit(X2, y)

    return (partial_fit_model1, partial_fit_model2,
            partial_fit_model3, partial_fit_model4)

Benchmarks

def build_x_y(ntrain, nfeat):
    X_train = np.empty((ntrain, nfeat))
    X_train[:, :] = rand(ntrain, nfeat)[:, :]
    X_trainsum = X_train.sum(axis=1)
    eps = rand(ntrain) - 0.5
    X_trainsum_ = X_trainsum + eps
    y_train = (X_trainsum_ >= X_trainsum).ravel().astype(int)
    return X_train, y_train


@ignore_warnings(category=(FutureWarning, DeprecationWarning))
def bench(n_obs, n_features, repeat=1000, verbose=False):
    res = []
    for n in n_obs:
        for nfeat in n_features:

            X_train, y_train = build_x_y(1000, nfeat)

            obs = dict(n_obs=n, nfeat=nfeat)

            fct1, fct2, fct3, fct4 = fcts_model(X_train, y_train)

            # creates different inputs to avoid caching in any ways
            Xs = []
            Xpolys = []
            for r in range(repeat):
                X, y = build_x_y(n, nfeat)
                Xs.append((X, y))
                Xpolys.append((PolynomialFeatures().fit_transform(X), y))

            # measure fct1
            r = len(Xs)
            st = time()
            for X, y in Xpolys:
                fct1(X, y)
            end = time()
            obs["time_sgd"] = (end - st) / r
            res.append(obs)

            # measures fct2
            st = time()
            for X, y in Xs:
                fct2(X, y)
            end = time()
            obs["time_pipe_skl"] = (end - st) / r
            res.append(obs)

            # measures fct3
            st = time()
            for X, y in Xs:
                fct3(X, y)
            end = time()
            obs["time_pipe_fast"] = (end - st) / r
            res.append(obs)

            # measures fct4
            st = time()
            for X, y in Xs:
                fct4(X, y)
            end = time()
            obs["time_pipe_slow"] = (end - st) / r
            res.append(obs)

            if verbose and (len(res) % 1 == 0 or n >= 10000):
                print("bench", len(res), ":", obs)

    return res

Plots

def plot_results(df, verbose=False):
    nrows = max(len(set(df.nfeat)), 2)
    ncols = max(1, 2)
    fig, ax = plt.subplots(nrows, ncols,
                           figsize=(nrows * 4, ncols * 4))
    colors = "gbry"
    row = 0
    for nfeat in sorted(set(df.nfeat)):
        pos = 0
        for _ in range(1):
            a = ax[row, pos]
            if row == ax.shape[0] - 1:
                a.set_xlabel("N observations", fontsize='x-small')
            if pos == 0:
                a.set_ylabel("Time (s) nfeat={}".format(nfeat),
                             fontsize='x-small')

            subset = df[df.nfeat == nfeat]
            if subset.shape[0] == 0:
                continue
            subset = subset.sort_values("n_obs")
            if verbose:
                print(subset)

            label = "SGD"
            subset.plot(x="n_obs", y="time_sgd", label=label, ax=a,
                        logx=True, logy=True, c=colors[0], style='--')
            label = "SGD-SKL"
            subset.plot(x="n_obs", y="time_pipe_skl", label=label, ax=a,
                        logx=True, logy=True, c=colors[1], style='--')
            label = "SGD-FAST"
            subset.plot(x="n_obs", y="time_pipe_fast", label=label, ax=a,
                        logx=True, logy=True, c=colors[2])
            label = "SGD-SLOW"
            subset.plot(x="n_obs", y="time_pipe_slow", label=label, ax=a,
                        logx=True, logy=True, c=colors[3])

            a.legend(loc=0, fontsize='x-small')
            if row == 0:
                a.set_title("--", fontsize='x-small')
            pos += 1
        row += 1

    plt.suptitle("Benchmark for Polynomial with SGDClassifier", fontsize=16)

Final function for the benchmark

def run_bench(repeat=100, verbose=False):
    n_obs = [10, 100, 1000]
    n_features = [5, 10, 50]

    with sklearn.config_context(assume_finite=True):
        start = time()
        results = bench(n_obs, n_features, repeat=repeat, verbose=verbose)
        end = time()

    results_df = pandas.DataFrame(results)
    print("Total time = %0.3f sec\n" % (end - start))

    # plot the results
    plot_results(results_df, verbose=verbose)
    return results_df

Run the benchmark

print("numpy:", numpy.__version__)
print("scikit-learn:", sklearn.__version__)
df = run_bench(verbose=True)
print(df)

plt.show()
Benchmark for Polynomial with SGDClassifier, --
numpy: 1.23.5
scikit-learn: 1.2.1
bench 4 : {'n_obs': 10, 'nfeat': 5, 'time_sgd': 0.0013249226997140795, 'time_pipe_skl': 0.0019261512299999595, 'time_pipe_fast': 0.001654766010469757, 'time_pipe_slow': 0.0029830967797897755}
bench 8 : {'n_obs': 10, 'nfeat': 10, 'time_sgd': 0.0013282932701986284, 'time_pipe_skl': 0.002122467309818603, 'time_pipe_fast': 0.0018563237501075492, 'time_pipe_slow': 0.006132730239769444}
bench 12 : {'n_obs': 10, 'nfeat': 50, 'time_sgd': 0.001581792570068501, 'time_pipe_skl': 0.0042063837201567365, 'time_pipe_fast': 0.003923654420068487, 'time_pipe_slow': 0.0948916418699082}
bench 16 : {'n_obs': 100, 'nfeat': 5, 'time_sgd': 0.0014259226596914233, 'time_pipe_skl': 0.002105059499735944, 'time_pipe_fast': 0.0018281825300073252, 'time_pipe_slow': 0.003142296050209552}
bench 20 : {'n_obs': 100, 'nfeat': 10, 'time_sgd': 0.0015108765999320894, 'time_pipe_skl': 0.0025323338998714463, 'time_pipe_fast': 0.0022405518998857587, 'time_pipe_slow': 0.006537817390053533}
bench 24 : {'n_obs': 100, 'nfeat': 50, 'time_sgd': 0.003097828699974343, 'time_pipe_skl': 0.007540988689870573, 'time_pipe_fast': 0.007151761099812574, 'time_pipe_slow': 0.10592318902025}
bench 28 : {'n_obs': 1000, 'nfeat': 5, 'time_sgd': 0.002426280700019561, 'time_pipe_skl': 0.0036441037902841342, 'time_pipe_fast': 0.0032889807398896664, 'time_pipe_slow': 0.004574504140182398}
bench 32 : {'n_obs': 1000, 'nfeat': 10, 'time_sgd': 0.0031518084503477438, 'time_pipe_skl': 0.0057958847098052504, 'time_pipe_fast': 0.005382269050460309, 'time_pipe_slow': 0.009759210420306773}
bench 36 : {'n_obs': 1000, 'nfeat': 50, 'time_sgd': 0.016945749250007792, 'time_pipe_skl': 0.04391203346021939, 'time_pipe_fast': 0.0465518391598016, 'time_pipe_slow': 0.15311013977974652}
Total time = 73.642 sec

    n_obs  nfeat  time_sgd  time_pipe_skl  time_pipe_fast  time_pipe_slow
0      10      5  0.001325       0.001926        0.001655        0.002983
1      10      5  0.001325       0.001926        0.001655        0.002983
2      10      5  0.001325       0.001926        0.001655        0.002983
3      10      5  0.001325       0.001926        0.001655        0.002983
12    100      5  0.001426       0.002105        0.001828        0.003142
13    100      5  0.001426       0.002105        0.001828        0.003142
14    100      5  0.001426       0.002105        0.001828        0.003142
15    100      5  0.001426       0.002105        0.001828        0.003142
24   1000      5  0.002426       0.003644        0.003289        0.004575
25   1000      5  0.002426       0.003644        0.003289        0.004575
26   1000      5  0.002426       0.003644        0.003289        0.004575
27   1000      5  0.002426       0.003644        0.003289        0.004575
    n_obs  nfeat  time_sgd  time_pipe_skl  time_pipe_fast  time_pipe_slow
4      10     10  0.001328       0.002122        0.001856        0.006133
5      10     10  0.001328       0.002122        0.001856        0.006133
6      10     10  0.001328       0.002122        0.001856        0.006133
7      10     10  0.001328       0.002122        0.001856        0.006133
16    100     10  0.001511       0.002532        0.002241        0.006538
17    100     10  0.001511       0.002532        0.002241        0.006538
18    100     10  0.001511       0.002532        0.002241        0.006538
19    100     10  0.001511       0.002532        0.002241        0.006538
28   1000     10  0.003152       0.005796        0.005382        0.009759
29   1000     10  0.003152       0.005796        0.005382        0.009759
30   1000     10  0.003152       0.005796        0.005382        0.009759
31   1000     10  0.003152       0.005796        0.005382        0.009759
    n_obs  nfeat  time_sgd  time_pipe_skl  time_pipe_fast  time_pipe_slow
8      10     50  0.001582       0.004206        0.003924        0.094892
9      10     50  0.001582       0.004206        0.003924        0.094892
10     10     50  0.001582       0.004206        0.003924        0.094892
11     10     50  0.001582       0.004206        0.003924        0.094892
20    100     50  0.003098       0.007541        0.007152        0.105923
21    100     50  0.003098       0.007541        0.007152        0.105923
22    100     50  0.003098       0.007541        0.007152        0.105923
23    100     50  0.003098       0.007541        0.007152        0.105923
32   1000     50  0.016946       0.043912        0.046552        0.153110
33   1000     50  0.016946       0.043912        0.046552        0.153110
34   1000     50  0.016946       0.043912        0.046552        0.153110
35   1000     50  0.016946       0.043912        0.046552        0.153110
    n_obs  nfeat  time_sgd  time_pipe_skl  time_pipe_fast  time_pipe_slow
0      10      5  0.001325       0.001926        0.001655        0.002983
1      10      5  0.001325       0.001926        0.001655        0.002983
2      10      5  0.001325       0.001926        0.001655        0.002983
3      10      5  0.001325       0.001926        0.001655        0.002983
4      10     10  0.001328       0.002122        0.001856        0.006133
5      10     10  0.001328       0.002122        0.001856        0.006133
6      10     10  0.001328       0.002122        0.001856        0.006133
7      10     10  0.001328       0.002122        0.001856        0.006133
8      10     50  0.001582       0.004206        0.003924        0.094892
9      10     50  0.001582       0.004206        0.003924        0.094892
10     10     50  0.001582       0.004206        0.003924        0.094892
11     10     50  0.001582       0.004206        0.003924        0.094892
12    100      5  0.001426       0.002105        0.001828        0.003142
13    100      5  0.001426       0.002105        0.001828        0.003142
14    100      5  0.001426       0.002105        0.001828        0.003142
15    100      5  0.001426       0.002105        0.001828        0.003142
16    100     10  0.001511       0.002532        0.002241        0.006538
17    100     10  0.001511       0.002532        0.002241        0.006538
18    100     10  0.001511       0.002532        0.002241        0.006538
19    100     10  0.001511       0.002532        0.002241        0.006538
20    100     50  0.003098       0.007541        0.007152        0.105923
21    100     50  0.003098       0.007541        0.007152        0.105923
22    100     50  0.003098       0.007541        0.007152        0.105923
23    100     50  0.003098       0.007541        0.007152        0.105923
24   1000      5  0.002426       0.003644        0.003289        0.004575
25   1000      5  0.002426       0.003644        0.003289        0.004575
26   1000      5  0.002426       0.003644        0.003289        0.004575
27   1000      5  0.002426       0.003644        0.003289        0.004575
28   1000     10  0.003152       0.005796        0.005382        0.009759
29   1000     10  0.003152       0.005796        0.005382        0.009759
30   1000     10  0.003152       0.005796        0.005382        0.009759
31   1000     10  0.003152       0.005796        0.005382        0.009759
32   1000     50  0.016946       0.043912        0.046552        0.153110
33   1000     50  0.016946       0.043912        0.046552        0.153110
34   1000     50  0.016946       0.043912        0.046552        0.153110
35   1000     50  0.016946       0.043912        0.046552        0.153110

Total running time of the script: ( 1 minutes 20.040 seconds)

Gallery generated by Sphinx-Gallery