scikit-learn · TomDLT · May 10, 2016 · May 4, 2016 · May 5, 2016 · May 5, 2016
diff --git a/benchmarks/bench_glm.py b/benchmarks/bench_glm.py
@@ -12,7 +12,7 @@
 
 if __name__ == '__main__':
 
-    import pylab as pl
+    import matplotlib.pyplot as plt
 
     n_iter = 40
 
@@ -46,13 +46,13 @@
         lasso.fit(X, Y)
         time_lasso[i] = total_seconds(datetime.now() - start)
 
-    pl.figure('scikit-learn GLM benchmark results')
-    pl.xlabel('Dimensions')
-    pl.ylabel('Time (s)')
-    pl.plot(dimensions, time_ridge, color='r')
-    pl.plot(dimensions, time_ols, color='g')
-    pl.plot(dimensions, time_lasso, color='b')
+    plt.figure('scikit-learn GLM benchmark results')
+    plt.xlabel('Dimensions')
+    plt.ylabel('Time (s)')
+    plt.plot(dimensions, time_ridge, color='r')
+    plt.plot(dimensions, time_ols, color='g')
+    plt.plot(dimensions, time_lasso, color='b')
 
-    pl.legend(['Ridge', 'OLS', 'LassoLars'], loc='upper left')
-    pl.axis('tight')
-    pl.show()
+    plt.legend(['Ridge', 'OLS', 'LassoLars'], loc='upper left')
+    plt.axis('tight')
+    plt.show()
diff --git a/benchmarks/bench_glmnet.py b/benchmarks/bench_glmnet.py
@@ -47,8 +47,8 @@ def bench(factory, X, Y, X_test, Y_test, ref_coef):
 if __name__ == '__main__':
     from glmnet.elastic_net import Lasso as GlmnetLasso
     from sklearn.linear_model import Lasso as ScikitLasso
-    # Delayed import of pylab
-    import pylab as pl
+    # Delayed import of matplotlib.pyplot
+    import matplotlib.pyplot as plt
 
     scikit_results = []
     glmnet_results = []
@@ -76,15 +76,15 @@ def bench(factory, X, Y, X_test, Y_test, ref_coef):
         print("benchmarking glmnet: ")
         glmnet_results.append(bench(GlmnetLasso, X, Y, X_test, Y_test, coef_))
 
-    pl.clf()
+    plt.clf()
     xx = range(0, n * step, step)
-    pl.title('Lasso regression on sample dataset (%d features)' % n_features)
-    pl.plot(xx, scikit_results, 'b-', label='scikit-learn')
-    pl.plot(xx, glmnet_results, 'r-', label='glmnet')
-    pl.legend()
-    pl.xlabel('number of samples to classify')
-    pl.ylabel('Time (s)')
-    pl.show()
+    plt.title('Lasso regression on sample dataset (%d features)' % n_features)
+    plt.plot(xx, scikit_results, 'b-', label='scikit-learn')
+    plt.plot(xx, glmnet_results, 'r-', label='glmnet')
+    plt.legend()
+    plt.xlabel('number of samples to classify')
+    plt.ylabel('Time (s)')
+    plt.show()
 
     # now do a benchmark where the number of points is fixed
     # and the variable is the number of features
@@ -117,12 +117,12 @@ def bench(factory, X, Y, X_test, Y_test, ref_coef):
         glmnet_results.append(bench(GlmnetLasso, X, Y, X_test, Y_test, coef_))
 
     xx = np.arange(100, 100 + n * step, step)
-    pl.figure('scikit-learn vs. glmnet benchmark results')
-    pl.title('Regression in high dimensional spaces (%d samples)' % n_samples)
-    pl.plot(xx, scikit_results, 'b-', label='scikit-learn')
-    pl.plot(xx, glmnet_results, 'r-', label='glmnet')
-    pl.legend()
-    pl.xlabel('number of features')
-    pl.ylabel('Time (s)')
-    pl.axis('tight')
-    pl.show()
+    plt.figure('scikit-learn vs. glmnet benchmark results')
+    plt.title('Regression in high dimensional spaces (%d samples)' % n_samples)
+    plt.plot(xx, scikit_results, 'b-', label='scikit-learn')
+    plt.plot(xx, glmnet_results, 'r-', label='glmnet')
+    plt.legend()
+    plt.xlabel('number of features')
+    plt.ylabel('Time (s)')
+    plt.axis('tight')
+    plt.show()
diff --git a/benchmarks/bench_lasso.py b/benchmarks/bench_lasso.py
@@ -59,7 +59,7 @@ def compute_bench(alpha, n_samples, n_features, precompute):
 
 if __name__ == '__main__':
     from sklearn.linear_model import Lasso, LassoLars
-    import pylab as pl
+    import matplotlib.pyplot as plt
 
     alpha = 0.01  # regularization parameter
 
@@ -68,28 +68,29 @@ def compute_bench(alpha, n_samples, n_features, precompute):
     lasso_results, lars_lasso_results = compute_bench(alpha, list_n_samples,
                                             [n_features], precompute=True)
 
-    pl.figure('scikit-learn LASSO benchmark results')
-    pl.subplot(211)
-    pl.plot(list_n_samples, lasso_results, 'b-',
+    plt.figure('scikit-learn LASSO benchmark results')
+    plt.subplot(211)
+    plt.plot(list_n_samples, lasso_results, 'b-',
                             label='Lasso')
-    pl.plot(list_n_samples, lars_lasso_results, 'r-',
+    plt.plot(list_n_samples, lars_lasso_results, 'r-',
                             label='LassoLars')
-    pl.title('precomputed Gram matrix, %d features, alpha=%s' % (n_features, alpha))
-    pl.legend(loc='upper left')
-    pl.xlabel('number of samples')
-    pl.ylabel('Time (s)')
-    pl.axis('tight')
+    plt.title('precomputed Gram matrix, %d features, alpha=%s' % (n_features,
+                            alpha))
+    plt.legend(loc='upper left')
+    plt.xlabel('number of samples')
+    plt.ylabel('Time (s)')
+    plt.axis('tight')
 
     n_samples = 2000
     list_n_features = np.linspace(500, 3000, 5).astype(np.int)
     lasso_results, lars_lasso_results = compute_bench(alpha, [n_samples],
                                            list_n_features, precompute=False)
-    pl.subplot(212)
-    pl.plot(list_n_features, lasso_results, 'b-', label='Lasso')
-    pl.plot(list_n_features, lars_lasso_results, 'r-', label='LassoLars')
-    pl.title('%d samples, alpha=%s' % (n_samples, alpha))
-    pl.legend(loc='upper left')
-    pl.xlabel('number of features')
-    pl.ylabel('Time (s)')
-    pl.axis('tight')
-    pl.show()
+    plt.subplot(212)
+    plt.plot(list_n_features, lasso_results, 'b-', label='Lasso')
+    plt.plot(list_n_features, lars_lasso_results, 'r-', label='LassoLars')
+    plt.title('%d samples, alpha=%s' % (n_samples, alpha))
+    plt.legend(loc='upper left')
+    plt.xlabel('number of features')
+    plt.ylabel('Time (s)')
+    plt.axis('tight')
+    plt.show()
diff --git a/benchmarks/bench_plot_neighbors.py b/benchmarks/bench_plot_neighbors.py
@@ -4,7 +4,7 @@
 from time import time
 
 import numpy as np
-import pylab as pl
+import matplotlib.pyplot as plt
 from matplotlib import ticker
 
 from sklearn import neighbors, datasets
@@ -106,7 +106,7 @@ def barplot_neighbors(Nrange=2 ** np.arange(1, 11),
             k_results_build[algorithm][i] = (t1 - t0)
             k_results_query[algorithm][i] = (t2 - t1)
 
-    pl.figure(figsize=(8, 11))
+    plt.figure(figsize=(8, 11))
 
     for (sbplt, vals, quantity,
          build_time, query_time) in [(311, Nrange, 'N',
@@ -118,8 +118,8 @@ def barplot_neighbors(Nrange=2 ** np.arange(1, 11),
                                      (313, krange, 'k',
                                       k_results_build,
                                       k_results_query)]:
-        ax = pl.subplot(sbplt, yscale='log')
-        pl.grid(True)
+        ax = plt.subplot(sbplt, yscale='log')
+        plt.grid(True)
 
         tick_vals = []
         tick_labels = []
@@ -131,21 +131,21 @@ def barplot_neighbors(Nrange=2 ** np.arange(1, 11),
             xvals = 0.1 + i * (1 + len(vals)) + np.arange(len(vals))
             width = 0.8
 
-            c_bar = pl.bar(xvals, build_time[alg] - bottom,
-                           width, bottom, color='r')
-            q_bar = pl.bar(xvals, query_time[alg],
-                           width, build_time[alg], color='b')
+            c_bar = plt.bar(xvals, build_time[alg] - bottom,
+                            width, bottom, color='r')
+            q_bar = plt.bar(xvals, query_time[alg],
+                            width, build_time[alg], color='b')
 
             tick_vals += list(xvals + 0.5 * width)
             tick_labels += ['%i' % val for val in vals]
 
-            pl.text((i + 0.02) / len(algorithms), 0.98, alg,
-                    transform=ax.transAxes,
-                    ha='left',
-                    va='top',
-                    bbox=dict(facecolor='w', edgecolor='w', alpha=0.5))
+            plt.text((i + 0.02) / len(algorithms), 0.98, alg,
+                     transform=ax.transAxes,
+                     ha='left',
+                     va='top',
+                     bbox=dict(facecolor='w', edgecolor='w', alpha=0.5))
 
-            pl.ylabel('Time (s)')
+            plt.ylabel('Time (s)')
 
         ax.xaxis.set_major_locator(ticker.FixedLocator(tick_vals))
         ax.xaxis.set_major_formatter(ticker.FixedFormatter(tick_labels))
@@ -166,20 +166,20 @@ def barplot_neighbors(Nrange=2 ** np.arange(1, 11),
 
         descr_string = descr_string[:-2]
 
-        pl.text(1.01, 0.5, title_string,
-                transform=ax.transAxes, rotation=-90,
-                ha='left', va='center', fontsize=20)
+        plt.text(1.01, 0.5, title_string,
+                 transform=ax.transAxes, rotation=-90,
+                 ha='left', va='center', fontsize=20)
 
-        pl.text(0.99, 0.5, descr_string,
-                transform=ax.transAxes, rotation=-90,
-                ha='right', va='center')
+        plt.text(0.99, 0.5, descr_string,
+                 transform=ax.transAxes, rotation=-90,
+                 ha='right', va='center')
 
-        pl.gcf().suptitle("%s data set" % dataset.capitalize(), fontsize=16)
+        plt.gcf().suptitle("%s data set" % dataset.capitalize(), fontsize=16)
 
-    pl.figlegend((c_bar, q_bar), ('construction', 'N-point query'),
-                 'upper right')
+    plt.figlegend((c_bar, q_bar), ('construction', 'N-point query'),
+                  'upper right')
 
 if __name__ == '__main__':
     barplot_neighbors(dataset='digits')
     barplot_neighbors(dataset='dense')
-    pl.show()
+    plt.show()
diff --git a/benchmarks/bench_plot_omp_lars.py b/benchmarks/bench_plot_omp_lars.py
@@ -105,19 +105,19 @@ def compute_bench(samples_range, features_range):
     results = compute_bench(samples_range, features_range)
     max_time = max(np.max(t) for t in results.values())
 
-    import pylab as pl
-    fig = pl.figure('scikit-learn OMP vs. LARS benchmark results')
+    import matplotlib.pyplot as plt
+    fig = plt.figure('scikit-learn OMP vs. LARS benchmark results')
     for i, (label, timings) in enumerate(sorted(results.iteritems())):
-        ax = fig.add_subplot(1, 2, i)
+        ax = fig.add_subplot(1, 2, i+1)
         vmax = max(1 - timings.min(), -1 + timings.max())
-        pl.matshow(timings, fignum=False, vmin=1 - vmax, vmax=1 + vmax)
+        plt.matshow(timings, fignum=False, vmin=1 - vmax, vmax=1 + vmax)
         ax.set_xticklabels([''] + map(str, samples_range))
         ax.set_yticklabels([''] + map(str, features_range))
-        pl.xlabel('n_samples')
-        pl.ylabel('n_features')
-        pl.title(label)
-
-    pl.subplots_adjust(0.1, 0.08, 0.96, 0.98, 0.4, 0.63)
-    ax = pl.axes([0.1, 0.08, 0.8, 0.06])
-    pl.colorbar(cax=ax, orientation='horizontal')
-    pl.show()
+        plt.xlabel('n_samples')
+        plt.ylabel('n_features')
+        plt.title(label)
+
+    plt.subplots_adjust(0.1, 0.08, 0.96, 0.98, 0.4, 0.63)
+    ax = plt.axes([0.1, 0.08, 0.8, 0.06])
+    plt.colorbar(cax=ax, orientation='horizontal')
+    plt.show()
diff --git a/benchmarks/bench_plot_parallel_pairwise.py b/benchmarks/bench_plot_parallel_pairwise.py
@@ -2,7 +2,7 @@
 # License: BSD 3 clause
 import time
 
-import pylab as pl
+import matplotlib.pyplot as plt
 
 from sklearn.utils import check_random_state
 from sklearn.metrics.pairwise import pairwise_distances
@@ -25,13 +25,13 @@ def plot(func):
         func(X, n_jobs=-1)
         multi_core.append(time.time() - start)
 
-    pl.figure('scikit-learn parallel %s benchmark results' % func.__name__)
-    pl.plot(sample_sizes, one_core, label="one core")
-    pl.plot(sample_sizes, multi_core, label="multi core")
-    pl.xlabel('n_samples')
-    pl.ylabel('Time (s)')
-    pl.title('Parallel %s' % func.__name__)
-    pl.legend()
+    plt.figure('scikit-learn parallel %s benchmark results' % func.__name__)
+    plt.plot(sample_sizes, one_core, label="one core")
+    plt.plot(sample_sizes, multi_core, label="multi core")
+    plt.xlabel('n_samples')
+    plt.ylabel('Time (s)')
+    plt.title('Parallel %s' % func.__name__)
+    plt.legend()
 
 def euclidean_distances(X, n_jobs):
     return pairwise_distances(X, metric="euclidean", n_jobs=n_jobs)
@@ -41,4 +41,4 @@ def rbf_kernels(X, n_jobs):
 
 plot(euclidean_distances)
 plot(rbf_kernels)
-pl.show()
+plt.show()
diff --git a/benchmarks/bench_plot_ward.py b/benchmarks/bench_plot_ward.py
@@ -6,7 +6,7 @@
 
 import numpy as np
 from scipy.cluster import hierarchy
-import pylab as pl
+import matplotlib.pyplot as plt
 
 from sklearn.cluster import AgglomerativeClustering
 
@@ -31,13 +31,13 @@
 
 ratio = scikits_time / scipy_time
 
-pl.figure("scikit-learn Ward's method benchmark results")
-pl.imshow(np.log(ratio), aspect='auto', origin="lower")
-pl.colorbar()
-pl.contour(ratio, levels=[1, ], colors='k')
-pl.yticks(range(len(n_features)), n_features.astype(np.int))
-pl.ylabel('N features')
-pl.xticks(range(len(n_samples)), n_samples.astype(np.int))
-pl.xlabel('N samples')
-pl.title("Scikit's time, in units of scipy time (log)")
-pl.show()
+plt.figure("scikit-learn Ward's method benchmark results")
+plt.imshow(np.log(ratio), aspect='auto', origin="lower")
+plt.colorbar()
+plt.contour(ratio, levels=[1, ], colors='k')
+plt.yticks(range(len(n_features)), n_features.astype(np.int))
+plt.ylabel('N features')
+plt.xticks(range(len(n_samples)), n_samples.astype(np.int))
+plt.xlabel('N samples')
+plt.title("Scikit's time, in units of scipy time (log)")
+plt.show()