Pushing the docs to dev/ for branch: main, commit 660e43aec705e0fb0efd23533ead6b4ed21540e6

Author: sklearn-ci

dev/_downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: Eustache Diemert <[email protected]>\n#          Maria Telenczuk <https://github.com/maikia>\n#          Guillaume Lemaitre <[email protected]>\n# License: BSD 3 clause\n\nimport time\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import datasets\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.svm import NuSVR\nfrom sklearn.ensemble import GradientBoostingRegressor\nfrom sklearn.linear_model import SGDClassifier\nfrom sklearn.metrics import hamming_loss\n\n# Initialize random generator\nnp.random.seed(0)"
+        "# Authors: Eustache Diemert <[email protected]>\n#          Maria Telenczuk <https://github.com/maikia>\n#          Guillaume Lemaitre <[email protected]>\n# License: BSD 3 clause\n\nimport time\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import datasets\nfrom sklearn.utils import shuffle\nfrom sklearn.metrics import mean_squared_error\nfrom sklearn.svm import NuSVR\nfrom sklearn.ensemble import GradientBoostingRegressor\nfrom sklearn.linear_model import SGDClassifier\nfrom sklearn.metrics import hamming_loss\n\n\n# Initialize random generator\nnp.random.seed(0)"
       ]
     },
     {
@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "def generate_data(case):\n    \"\"\"Generate regression/classification data.\"\"\"\n    if case == \"regression\":\n        X, y = datasets.load_diabetes(return_X_y=True)\n        train_size = 0.8\n    elif case == \"classification\":\n        X, y = datasets.fetch_20newsgroups_vectorized(subset=\"all\", return_X_y=True)\n        train_size = 0.4  # to make the example run faster\n\n    X_train, X_test, y_train, y_test = train_test_split(\n        X, y, train_size=train_size, random_state=0\n    )\n\n    data = {\"X_train\": X_train, \"X_test\": X_test, \"y_train\": y_train, \"y_test\": y_test}\n    return data\n\n\nregression_data = generate_data(\"regression\")\nclassification_data = generate_data(\"classification\")"
+        "def generate_data(case):\n    \"\"\"Generate regression/classification data.\"\"\"\n    if case == \"regression\":\n        X, y = datasets.load_diabetes(return_X_y=True)\n    elif case == \"classification\":\n        X, y = datasets.fetch_20newsgroups_vectorized(subset=\"all\", return_X_y=True)\n    X, y = shuffle(X, y)\n    offset = int(X.shape[0] * 0.8)\n    X_train, y_train = X[:offset], y[:offset]\n    X_test, y_test = X[offset:], y[offset:]\n\n    data = {\"X_train\": X_train, \"X_test\": X_test, \"y_train\": y_train, \"y_test\": y_test}\n    return data\n\n\nregression_data = generate_data(\"regression\")\nclassification_data = generate_data(\"classification\")"
       ]
     },
     {
@@ -80,7 +80,7 @@
       },
       "outputs": [],
       "source": [
-        "def _count_nonzero_coefficients(estimator):\n    a = estimator.coef_.toarray()\n    return np.count_nonzero(a)\n\n\nconfigurations = [\n    {\n        \"estimator\": SGDClassifier,\n        \"tuned_params\": {\n            \"penalty\": \"elasticnet\",\n            \"alpha\": 0.001,\n            \"loss\": \"modified_huber\",\n            \"fit_intercept\": True,\n            \"tol\": 1e-3,\n        },\n        \"changing_param\": \"l1_ratio\",\n        \"changing_param_values\": [0.25, 0.5, 0.75, 0.9],\n        \"complexity_label\": \"non_zero coefficients\",\n        \"complexity_computer\": _count_nonzero_coefficients,\n        \"prediction_performance_computer\": hamming_loss,\n        \"prediction_performance_label\": \"Hamming Loss (Misclassification Ratio)\",\n        \"postfit_hook\": lambda x: x.sparsify(),\n        \"data\": classification_data,\n        \"n_samples\": 5,\n    },\n    {\n        \"estimator\": NuSVR,\n        \"tuned_params\": {\"C\": 1e3, \"gamma\": 2 ** -15},\n        \"changing_param\": \"nu\",\n        \"changing_param_values\": [0.05, 0.1, 0.2, 0.35, 0.5],\n        \"complexity_label\": \"n_support_vectors\",\n        \"complexity_computer\": lambda x: len(x.support_vectors_),\n        \"data\": regression_data,\n        \"postfit_hook\": lambda x: x,\n        \"prediction_performance_computer\": mean_squared_error,\n        \"prediction_performance_label\": \"MSE\",\n        \"n_samples\": 15,\n    },\n    {\n        \"estimator\": GradientBoostingRegressor,\n        \"tuned_params\": {\n            \"loss\": \"squared_error\",\n            \"learning_rate\": 0.05,\n            \"max_depth\": 2,\n        },\n        \"changing_param\": \"n_estimators\",\n        \"changing_param_values\": [10, 25, 50, 75, 100],\n        \"complexity_label\": \"n_trees\",\n        \"complexity_computer\": lambda x: x.n_estimators,\n        \"data\": regression_data,\n        \"postfit_hook\": lambda x: x,\n        \"prediction_performance_computer\": mean_squared_error,\n        \"prediction_performance_label\": \"MSE\",\n        \"n_samples\": 15,\n    },\n]"
+        "def _count_nonzero_coefficients(estimator):\n    a = estimator.coef_.toarray()\n    return np.count_nonzero(a)\n\n\nconfigurations = [\n    {\n        \"estimator\": SGDClassifier,\n        \"tuned_params\": {\n            \"penalty\": \"elasticnet\",\n            \"alpha\": 0.001,\n            \"loss\": \"modified_huber\",\n            \"fit_intercept\": True,\n            \"tol\": 1e-3,\n        },\n        \"changing_param\": \"l1_ratio\",\n        \"changing_param_values\": [0.25, 0.5, 0.75, 0.9],\n        \"complexity_label\": \"non_zero coefficients\",\n        \"complexity_computer\": _count_nonzero_coefficients,\n        \"prediction_performance_computer\": hamming_loss,\n        \"prediction_performance_label\": \"Hamming Loss (Misclassification Ratio)\",\n        \"postfit_hook\": lambda x: x.sparsify(),\n        \"data\": classification_data,\n        \"n_samples\": 30,\n    },\n    {\n        \"estimator\": NuSVR,\n        \"tuned_params\": {\"C\": 1e3, \"gamma\": 2 ** -15},\n        \"changing_param\": \"nu\",\n        \"changing_param_values\": [0.1, 0.25, 0.5, 0.75, 0.9],\n        \"complexity_label\": \"n_support_vectors\",\n        \"complexity_computer\": lambda x: len(x.support_vectors_),\n        \"data\": regression_data,\n        \"postfit_hook\": lambda x: x,\n        \"prediction_performance_computer\": mean_squared_error,\n        \"prediction_performance_label\": \"MSE\",\n        \"n_samples\": 30,\n    },\n    {\n        \"estimator\": GradientBoostingRegressor,\n        \"tuned_params\": {\"loss\": \"squared_error\"},\n        \"changing_param\": \"n_estimators\",\n        \"changing_param_values\": [10, 50, 100, 200, 500],\n        \"complexity_label\": \"n_trees\",\n        \"complexity_computer\": lambda x: x.n_estimators,\n        \"data\": regression_data,\n        \"postfit_hook\": lambda x: x,\n        \"prediction_performance_computer\": mean_squared_error,\n        \"prediction_performance_label\": \"MSE\",\n        \"n_samples\": 30,\n    },\n]"
       ]
     },
     {
@@ -98,7 +98,7 @@
       },
       "outputs": [],
       "source": [
-        "def plot_influence(conf, mse_values, prediction_times, complexities):\n    \"\"\"\n    Plot influence of model complexity on both accuracy and latency.\n    \"\"\"\n\n    fig = plt.figure()\n    fig.subplots_adjust(right=0.75)\n\n    # first axes (prediction error)\n    ax1 = fig.add_subplot(111)\n    line1 = ax1.plot(complexities, mse_values, c=\"tab:blue\", ls=\"-\")[0]\n    ax1.set_xlabel(\"Model Complexity (%s)\" % conf[\"complexity_label\"])\n    y1_label = conf[\"prediction_performance_label\"]\n    ax1.set_ylabel(y1_label)\n\n    ax1.spines[\"left\"].set_color(line1.get_color())\n    ax1.yaxis.label.set_color(line1.get_color())\n    ax1.tick_params(axis=\"y\", colors=line1.get_color())\n\n    # second axes (latency)\n    ax2 = fig.add_subplot(111, sharex=ax1, frameon=False)\n    line2 = ax2.plot(complexities, prediction_times, c=\"tab:orange\", ls=\"-\")[0]\n    ax2.yaxis.tick_right()\n    ax2.yaxis.set_label_position(\"right\")\n    y2_label = \"Time (s)\"\n    ax2.set_ylabel(y2_label)\n    ax1.spines[\"right\"].set_color(line2.get_color())\n    ax2.yaxis.label.set_color(line2.get_color())\n    ax2.tick_params(axis=\"y\", colors=line2.get_color())\n\n    plt.legend(\n        (line1, line2), (\"prediction error\", \"prediction latency\"), loc=\"upper right\"\n    )\n\n    plt.title(\n        \"Influence of varying '%s' on %s\"\n        % (conf[\"changing_param\"], conf[\"estimator\"].__name__)\n    )\n\n\nfor conf in configurations:\n    prediction_performances, prediction_times, complexities = benchmark_influence(conf)\n    plot_influence(conf, prediction_performances, prediction_times, complexities)\nplt.show()"
+        "def plot_influence(conf, mse_values, prediction_times, complexities):\n    \"\"\"\n    Plot influence of model complexity on both accuracy and latency.\n    \"\"\"\n\n    fig = plt.figure()\n    fig.subplots_adjust(right=0.75)\n\n    # first axes (prediction error)\n    ax1 = fig.add_subplot(111)\n    line1 = ax1.plot(complexities, mse_values, c=\"tab:blue\", ls=\"-\")[0]\n    ax1.set_xlabel(\"Model Complexity (%s)\" % conf[\"complexity_label\"])\n    y1_label = conf[\"prediction_performance_label\"]\n    ax1.set_ylabel(y1_label)\n\n    ax1.spines[\"left\"].set_color(line1.get_color())\n    ax1.yaxis.label.set_color(line1.get_color())\n    ax1.tick_params(axis=\"y\", colors=line1.get_color())\n\n    # second axes (latency)\n    ax2 = fig.add_subplot(111, sharex=ax1, frameon=False)\n    line2 = ax2.plot(complexities, prediction_times, c=\"tab:orange\", ls=\"-\")[0]\n    ax2.yaxis.tick_right()\n    ax2.yaxis.set_label_position(\"right\")\n    y2_label = \"Time (s)\"\n    ax2.set_ylabel(y2_label)\n    ax1.spines[\"right\"].set_color(line2.get_color())\n    ax2.yaxis.label.set_color(line2.get_color())\n    ax2.tick_params(axis=\"y\", colors=line2.get_color())\n\n    plt.legend((line1, line2), (\"prediction error\", \"latency\"), loc=\"upper right\")\n\n    plt.title(\n        \"Influence of varying '%s' on %s\"\n        % (conf[\"changing_param\"], conf[\"estimator\"].__name__)\n    )\n\n\nfor conf in configurations:\n    prediction_performances, prediction_times, complexities = benchmark_influence(conf)\n    plot_influence(conf, prediction_performances, prediction_times, complexities)\nplt.show()"
       ]
     },
     {

dev/_downloads/3ed102fa8211c8d36f2331f0c5e1dcef/plot_model_complexity_influence.ipynb

@@ -42,13 +42,14 @@
 import matplotlib.pyplot as plt
 
 from sklearn import datasets
-from sklearn.model_selection import train_test_split
+from sklearn.utils import shuffle
 from sklearn.metrics import mean_squared_error
 from sklearn.svm import NuSVR
 from sklearn.ensemble import GradientBoostingRegressor
 from sklearn.linear_model import SGDClassifier
 from sklearn.metrics import hamming_loss
 
+
 # Initialize random generator
 np.random.seed(0)
 
@@ -71,14 +72,12 @@ def generate_data(case):
     """Generate regression/classification data."""
     if case == "regression":
         X, y = datasets.load_diabetes(return_X_y=True)
-        train_size = 0.8
     elif case == "classification":
         X, y = datasets.fetch_20newsgroups_vectorized(subset="all", return_X_y=True)
-        train_size = 0.4  # to make the example run faster
-
-    X_train, X_test, y_train, y_test = train_test_split(
-        X, y, train_size=train_size, random_state=0
-    )
+    X, y = shuffle(X, y)
+    offset = int(X.shape[0] * 0.8)
+    X_train, y_train = X[:offset], y[:offset]
+    X_test, y_test = X[offset:], y[offset:]
 
     data = {"X_train": X_train, "X_test": X_test, "y_train": y_train, "y_test": y_test}
     return data
@@ -175,37 +174,33 @@ def _count_nonzero_coefficients(estimator):
         "prediction_performance_label": "Hamming Loss (Misclassification Ratio)",
         "postfit_hook": lambda x: x.sparsify(),
         "data": classification_data,
-        "n_samples": 5,
+        "n_samples": 30,
     },
     {
         "estimator": NuSVR,
         "tuned_params": {"C": 1e3, "gamma": 2 ** -15},
         "changing_param": "nu",
-        "changing_param_values": [0.05, 0.1, 0.2, 0.35, 0.5],
+        "changing_param_values": [0.1, 0.25, 0.5, 0.75, 0.9],
         "complexity_label": "n_support_vectors",
         "complexity_computer": lambda x: len(x.support_vectors_),
         "data": regression_data,
         "postfit_hook": lambda x: x,
         "prediction_performance_computer": mean_squared_error,
         "prediction_performance_label": "MSE",
-        "n_samples": 15,
+        "n_samples": 30,
     },
     {
         "estimator": GradientBoostingRegressor,
-        "tuned_params": {
-            "loss": "squared_error",
-            "learning_rate": 0.05,
-            "max_depth": 2,
-        },
+        "tuned_params": {"loss": "squared_error"},
         "changing_param": "n_estimators",
-        "changing_param_values": [10, 25, 50, 75, 100],
+        "changing_param_values": [10, 50, 100, 200, 500],
         "complexity_label": "n_trees",
         "complexity_computer": lambda x: x.n_estimators,
         "data": regression_data,
         "postfit_hook": lambda x: x,
         "prediction_performance_computer": mean_squared_error,
         "prediction_performance_label": "MSE",
-        "n_samples": 15,
+        "n_samples": 30,
     },
 ]
 
@@ -260,9 +255,7 @@ def plot_influence(conf, mse_values, prediction_times, complexities):
     ax2.yaxis.label.set_color(line2.get_color())
     ax2.tick_params(axis="y", colors=line2.get_color())
 
-    plt.legend(
-        (line1, line2), ("prediction error", "prediction latency"), loc="upper right"
-    )
+    plt.legend((line1, line2), ("prediction error", "latency"), loc="upper right")
 
     plt.title(
         "Influence of varying '%s' on %s"
@@ -275,6 +268,7 @@ def plot_influence(conf, mse_values, prediction_times, complexities):
     plot_influence(conf, prediction_performances, prediction_times, complexities)
 plt.show()
 
+
 ##############################################################################
 # Conclusion
 # ----------