mirror of
https://github.com/ArthurDanjou/ml_exercises.git
synced 2026-01-27 10:20:35 +01:00
update versions
This commit is contained in:
franzi
@@ -22,6 +22,8 @@
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"from matplotlib.colors import ListedColormap\n",
|
||||
"from sklearn.datasets import make_moons\n",
|
||||
"from sklearn.preprocessing import StandardScaler\n",
|
||||
"from sklearn.inspection import DecisionBoundaryDisplay\n",
|
||||
"# don't get unneccessary warnings\n",
|
||||
"import warnings\n",
|
||||
"warnings.simplefilter(action='ignore', category=FutureWarning)"
|
||||
@@ -54,39 +56,22 @@
|
||||
"def plot_classification(X, Y, model=None):\n",
|
||||
" # plot a classification dataset (and model predictions)\n",
|
||||
" plt.figure()\n",
|
||||
" x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5\n",
|
||||
" y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5\n",
|
||||
" xx, yy = np.meshgrid(np.linspace(x_min, x_max, 250),\n",
|
||||
" np.linspace(y_min, y_max, 250))\n",
|
||||
" cm = plt.cm.RdBu\n",
|
||||
" cm_bright = ListedColormap(['#FF0000', '#0000FF'])\n",
|
||||
" if model is not None:\n",
|
||||
" try:\n",
|
||||
" Z = model.decision_function(np.c_[xx.ravel(), yy.ravel()])\n",
|
||||
" alpha = 0.8\n",
|
||||
" except:\n",
|
||||
" # decision tree\n",
|
||||
" Z = model.predict(np.c_[xx.ravel(), yy.ravel()])\n",
|
||||
" alpha = 0.4\n",
|
||||
" # Put the result into a color plot\n",
|
||||
" Z = Z.reshape(xx.shape)\n",
|
||||
" plt.contourf(xx, yy, Z, cmap=cm, alpha=alpha)\n",
|
||||
" # Plot the training points\n",
|
||||
" plt.scatter(X[:, 0], X[:, 1], s=20, c=Y, cmap=cm_bright, label=\"data samples\")\n",
|
||||
" plt.xlim(xx.min(), xx.max())\n",
|
||||
" plt.ylim(yy.min(), yy.max())\n",
|
||||
" plt.xlabel(\"feature 1\")\n",
|
||||
" plt.ylabel(\"feature 2\")\n",
|
||||
" DecisionBoundaryDisplay.from_estimator(\n",
|
||||
" model, X, cmap=plt.cm.RdBu, alpha=0.8, eps=0.5, xlabel=\"feature 1\", ylabel=\"feature 2\", ax=plt.gca()\n",
|
||||
" )\n",
|
||||
" # plot the training points\n",
|
||||
" plt.scatter(X[:, 0], X[:, 1], s=20, c=Y, cmap=ListedColormap(['#FF0000', '#0000FF']), label=\"data samples\")\n",
|
||||
" plt.title(\"Classification Problem\")\n",
|
||||
" plt.colorbar()\n",
|
||||
"\n",
|
||||
" \n",
|
||||
"def get_linear_regression():\n",
|
||||
" # generate noisy linear regression dataset\n",
|
||||
" np.random.seed(15)\n",
|
||||
" X = np.random.rand(n_train_reg, 1)\n",
|
||||
" y = -2.5 + 5*X\n",
|
||||
" y += np.random.randn(n_train_reg, 1) * 0.4\n",
|
||||
" return X, y.flatten()\n",
|
||||
" return StandardScaler(with_std=False).fit_transform(X), y.flatten()\n",
|
||||
"\n",
|
||||
"def get_linear_outlier():\n",
|
||||
" # generate linear regression dataset with outliers\n",
|
||||
@@ -95,7 +80,7 @@
|
||||
" y = -2.5 + 5*X\n",
|
||||
" y += np.random.randn(n_train_reg, 1) * 0.05\n",
|
||||
" y[(X>0.7) & (X<0.73)] = 10\n",
|
||||
" return X, y.flatten()\n",
|
||||
" return StandardScaler(with_std=False).fit_transform(X), y.flatten()\n",
|
||||
"\n",
|
||||
"def get_nonlinear_regression():\n",
|
||||
" # generate noisy non-linear regression dataset\n",
|
||||
@@ -103,7 +88,7 @@
|
||||
" X = np.random.rand(n_train_reg, 1) * np.pi * 2.\n",
|
||||
" y = np.sin(X)\n",
|
||||
" y += np.random.randn(n_train_reg, 1) * 0.2\n",
|
||||
" return X, y.flatten()\n",
|
||||
" return StandardScaler().fit_transform(X), y.flatten()\n",
|
||||
"\n",
|
||||
"def get_linear_classification_1f():\n",
|
||||
" # generate classification dataset with 1 informative feature\n",
|
||||
@@ -117,7 +102,7 @@
|
||||
" y = np.zeros(n_train_clf, dtype=int)\n",
|
||||
" y[n_train_clf//2:] = 1\n",
|
||||
" rndidx = np.random.permutation(len(y))\n",
|
||||
" return X[rndidx], y[rndidx]\n",
|
||||
" return StandardScaler().fit_transform(X[rndidx]), y[rndidx]\n",
|
||||
"\n",
|
||||
"def get_linear_classification_2f():\n",
|
||||
" # generate classification dataset with 2 informative features\n",
|
||||
@@ -132,11 +117,12 @@
|
||||
" y = np.zeros(n_train_clf, dtype=int)\n",
|
||||
" y[n_train_clf//2:] = 1\n",
|
||||
" rndidx = np.random.permutation(len(y))\n",
|
||||
" return X[rndidx], y[rndidx]\n",
|
||||
" return StandardScaler().fit_transform(X[rndidx]), y[rndidx]\n",
|
||||
"\n",
|
||||
"def get_nonlinear_classification():\n",
|
||||
" # generate non-linear classification dataset\n",
|
||||
" return make_moons(n_samples=n_train_clf, noise=0.3, random_state=1)"
|
||||
" X, y = make_moons(n_samples=n_train_clf, noise=0.3, random_state=1)\n",
|
||||
" return StandardScaler().fit_transform(X), y"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -248,6 +234,59 @@
|
||||
"print(f\"f(x) = sigmoid({model.intercept_[0]:.3f} + {model.coef_[0, 0]:.3f} * x_1 + {model.coef_[0, 1]:.3f} * x_2)\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Feed-Forward Neural Network (Multi-Layer Perceptron)\n",
|
||||
"\n",
|
||||
"After reading the chapter on neural networks, test them here on different datasets and experiment with their hyperparameter settings.\n",
|
||||
"\n",
|
||||
"**Questions:**\n",
|
||||
"- What do you observe when you change the activation function to `'relu'` for the 3rd regression dataset?"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from sklearn.neural_network import MLPRegressor, MLPClassifier"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Neural network for regression:\n",
|
||||
"# alpha (> 0): regularization (higher values = more regularization)\n",
|
||||
"# hidden_layer_sizes (tuple of ints): number of units in the hidden layers\n",
|
||||
"# activation (one of 'identity', 'logistic', 'tanh', 'relu'): non-linear activation function between layers\n",
|
||||
"X, y = X_reg_3, y_reg_3\n",
|
||||
"model = MLPRegressor(alpha=1e-05, hidden_layer_sizes=(15,), activation=\"tanh\", solver=\"lbfgs\", random_state=1)\n",
|
||||
"model.fit(X, y)\n",
|
||||
"plot_regression(X, y, model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Neural network for classification:\n",
|
||||
"# alpha (> 0): regularization (higher values = more regularization)\n",
|
||||
"# hidden_layer_sizes (tuple of ints): number of units in the hidden layers\n",
|
||||
"# activation (one of 'identity', 'logistic', 'tanh', 'relu'): non-linear activation function between layers\n",
|
||||
"X, y = X_clf_3, y_clf_3\n",
|
||||
"model = MLPClassifier(alpha=1e-05, hidden_layer_sizes=(25, 5), activation=\"relu\", solver=\"adam\", max_iter=1000, random_state=1)\n",
|
||||
"model.fit(X, y)\n",
|
||||
"plot_classification(X, y, model)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
@@ -468,7 +507,7 @@
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
@@ -482,7 +521,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.5"
|
||||
"version": "3.10.2"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Reference in New Issue
Block a user