schuetoliver
/
handson-ml
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Sync notebook with book's code examples, and better identify extra code

main
Aurélien Geron 2022-02-19 18:17:36 +13:00
parent 1c2421fc88
commit b63019fd28
9 changed files with 318 additions and 301 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
02_end_to_end_machine_learning_project.ipynb
View File

@ -177,7 +177,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – code to save the figures as high-res PNGs for the book\n",
"# extra code – code to save the figures as high-res PNGs for the book\n",
"\n",
"IMAGES_PATH = Path() / \"images\" / \"end_to_end_project\"\n",
"IMAGES_PATH.mkdir(parents=True, exist_ok=True)\n",
@ -197,7 +197,7 @@
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"# not in the book – the next 5 lines define the default font sizes\n",
"# extra code – the next 5 lines define the default font sizes\n",
"plt.rc('font', size=14)\n",
"plt.rc('axes', labelsize=14, titlesize=14)\n",
"plt.rc('legend', fontsize=14)\n",
@ -205,7 +205,7 @@
"plt.rc('ytick', labelsize=10)\n",
"\n",
"housing.hist(bins=50, figsize=(12, 8))\n",
"save_fig(\"attribute_histogram_plots\") # not in the book\n",
"save_fig(\"attribute_histogram_plots\") # extra code\n",
"plt.show()"
]
},
@ -351,7 +351,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – shows how to compute the 10.7% proba of getting a bad sample\n",
"# extra code – shows how to compute the 10.7% proba of getting a bad sample\n",
"\n",
"from scipy.stats import binom\n",
"\n",
@ -375,7 +375,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – shows another way to estimate the probability of bad sample\n",
"# extra code – shows another way to estimate the probability of bad sample\n",
"\n",
"np.random.seed(42)\n",
"\n",
@ -403,7 +403,7 @@
"housing[\"income_cat\"].value_counts().sort_index().plot.bar(rot=0, grid=True)\n",
"plt.xlabel(\"Income category\")\n",
"plt.ylabel(\"Number of districts\")\n",
"save_fig(\"housing_income_cat_bar_plot\") # not in the book\n",
"save_fig(\"housing_income_cat_bar_plot\") # extra code\n",
"plt.show()"
]
},
@ -464,7 +464,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code computes the data for Figure 2–10\n",
"# extra code – computes the data for Figure 2–10\n",
"\n",
"def income_cat_proportions(data):\n",
" return data[\"income_cat\"].value_counts() / len(data)\n",
@ -524,7 +524,7 @@
"outputs": [],
"source": [
"housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", grid=True)\n",
"save_fig(\"bad_visualization_plot\") # not in the book\n",
"save_fig(\"bad_visualization_plot\") # extra code\n",
"plt.show()"
]
},
@ -535,7 +535,7 @@
"outputs": [],
"source": [
"housing.plot(kind=\"scatter\", x=\"longitude\", y=\"latitude\", grid=True, alpha=0.2)\n",
"save_fig(\"better_visualization_plot\") # not in the book\n",
"save_fig(\"better_visualization_plot\") # extra code\n",
"plt.show()"
]
},
@ -549,7 +549,7 @@
" s=housing[\"population\"] / 100, label=\"population\",\n",
" c=\"median_house_value\", cmap=\"jet\", colorbar=True,\n",
" legend=True, sharex=False, figsize=(10, 7))\n",
"save_fig(\"housing_prices_scatterplot\") # not in the book\n",
"save_fig(\"housing_prices_scatterplot\") # extra code\n",
"plt.show()"
]
},
@ -573,7 +573,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates the first figure in the chapter\n",
"# extra code – this cell generates the first figure in the chapter\n",
"\n",
"# Download the California image\n",
"filename = \"california.png\"\n",
@ -638,7 +638,7 @@
"attributes = [\"median_house_value\", \"median_income\", \"total_rooms\",\n",
" \"housing_median_age\"]\n",
"scatter_matrix(housing[attributes], figsize=(12, 8))\n",
"save_fig(\"scatter_matrix_plot\") # not in the book\n",
"save_fig(\"scatter_matrix_plot\") # extra code\n",
"plt.show()"
]
},
@ -650,7 +650,7 @@
"source": [
"housing.plot(kind=\"scatter\", x=\"median_income\", y=\"median_house_value\",\n",
" alpha=0.1, grid=True)\n",
"save_fig(\"income_vs_house_value_scatterplot\") # not in the book\n",
"save_fig(\"income_vs_house_value_scatterplot\") # extra code\n",
"plt.show()"
]
},
@ -1195,7 +1195,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates Figure 2–17\n",
"# extra code – this cell generates Figure 2–17\n",
"fig, axs = plt.subplots(1, 2, figsize=(8, 3), sharey=True)\n",
"housing[\"population\"].hist(ax=axs[0], bins=50)\n",
"housing[\"population\"].apply(np.log).hist(ax=axs[1], bins=50)\n",
@ -1219,7 +1219,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code just shows that we get a uniform distribution\n",
"# extra code – just shows that we get a uniform distribution\n",
"percentiles = [np.percentile(housing[\"median_income\"], p)\n",
" for p in range(1, 100)]\n",
"flattened_median_income = pd.cut(housing[\"median_income\"],\n",
@ -1251,7 +1251,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates Figure 2–18\n",
"# extra code – this cell generates Figure 2–18\n",
"\n",
"ages = np.linspace(housing[\"housing_median_age\"].min(),\n",
" housing[\"housing_median_age\"].max(),\n",
@ -1488,7 +1488,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates Figure 2–19\n",
"# extra code – this cell generates Figure 2–19\n",
"\n",
"housing_renamed = housing.rename(columns={\n",
" \"latitude\": \"Latitude\", \"longitude\": \"Longitude\",\n",
@ -1638,7 +1638,7 @@
"metadata": {},
"outputs": [],
"source": [
"df_housing_num_prepared.head(2) # not in the book"
"df_housing_num_prepared.head(2) # extra code"
]
},
{
@ -1737,7 +1737,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code shows that we can get a DataFrame out if we want\n",
"# extra code – shows that we can get a DataFrame out if we want\n",
"housing_prepared_fr = pd.DataFrame(\n",
" housing_prepared,\n",
" columns=preprocessing.get_feature_names_out(),\n",
@ -1866,7 +1866,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code computes the error ratios discussed in the book\n",
"# extra code – computes the error ratios discussed in the book\n",
"error_ratios = housing_predictions[:5].round(-2) / housing_labels.iloc[:5].values - 1\n",
"print(\", \".join([f\"{100 * ratio:.1f}%\" for ratio in error_ratios]))"
]
@ -1942,7 +1942,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code computes the error stats for the linear model\n",
"# extra code – computes the error stats for the linear model\n",
"lin_rmses = -cross_val_score(lin_reg, housing, housing_labels,\n",
" scoring=\"neg_root_mean_squared_error\", cv=10)\n",
"pd.Series(lin_rmses).describe()"
@ -2062,7 +2062,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code shows part of the output of get_params().keys()\n",
"# extra code – shows part of the output of get_params().keys()\n",
"print(str(full_pipeline.get_params().keys())[:1000] + \"...\")"
]
},
@ -2107,7 +2107,7 @@
"cv_res = pd.DataFrame(grid_search.cv_results_)\n",
"cv_res.sort_values(by=\"mean_test_score\", ascending=False, inplace=True)\n",
"\n",
"# not in the book – these few lines of code just make the DataFrame look nicer\n",
"# extra code – these few lines of code just make the DataFrame look nicer\n",
"cv_res = cv_res[[\"param_preprocessing__geo__n_clusters\",\n",
" \"param_random_forest__max_features\", \"split0_test_score\",\n",
" \"split1_test_score\", \"split2_test_score\", \"mean_test_score\"]]\n",
@ -2174,7 +2174,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code displays the random search results\n",
"# extra code – displays the random search results\n",
"cv_res = pd.DataFrame(rnd_search.cv_results_)\n",
"cv_res.sort_values(by=\"mean_test_score\", ascending=False, inplace=True)\n",
"cv_res = cv_res[[\"param_preprocessing__geo__n_clusters\",\n",
@ -2213,7 +2213,7 @@
},
"outputs": [],
"source": [
"# not in the book – plots a few distributions you can use in randomized search\n",
"# extra code – plots a few distributions you can use in randomized search\n",
"\n",
"from scipy.stats import randint, uniform, geom, expon\n",
"\n",
@ -2275,7 +2275,7 @@
},
"outputs": [],
"source": [
"# not in the book – shows the difference between expon and reciprocal\n",
"# extra code – shows the difference between expon and reciprocal\n",
"\n",
"from scipy.stats import reciprocal\n",
"\n",
@ -2410,7 +2410,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – shows how to compute a confidence interval for the RMSE\n",
"# extra code – shows how to compute a confidence interval for the RMSE\n",
"m = len(squared_errors)\n",
"mean = squared_errors.mean()\n",
"tscore = stats.t.ppf((1 + confidence) / 2, df=m - 1)\n",
@ -2431,7 +2431,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – computes a confidence interval again using z-score\n",
"# extra code – computes a confidence interval again using z-score\n",
"zscore = stats.norm.ppf((1 + confidence) / 2)\n",
"zmargin = zscore * squared_errors.std(ddof=1) / np.sqrt(m)\n",
"np.sqrt(mean - zmargin), np.sqrt(mean + zmargin)"
@ -2477,7 +2477,7 @@
"source": [
"import joblib\n",
"\n",
"# not in the book – excluded for conciseness\n",
"# extra code – excluded for conciseness\n",
"from sklearn.cluster import KMeans\n",
"from sklearn.base import BaseEstimator, TransformerMixin\n",
"from sklearn.metrics.pairwise import rbf_kernel\n",

60
03_classification.ipynb
View File

@ -142,7 +142,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – it's a bit too long\n",
"# extra code – it's a bit too long\n",
"print(mnist.DESCR)"
]
},
@ -152,7 +152,7 @@
"metadata": {},
"outputs": [],
"source": [
"mnist.keys() # not in the book – we only use data and target in this notebook"
"mnist.keys() # extra code – we only use data and target in this notebook"
]
},
{
@ -216,7 +216,7 @@
"\n",
"some_digit = X[0]\n",
"plot_digit(some_digit)\n",
"save_fig(\"some_digit_plot\") # not in the book\n",
"save_fig(\"some_digit_plot\") # extra code\n",
"plt.show()"
]
},
@ -235,7 +235,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates Figure 3–2\n",
"# extra code – this cell generates and saves Figure 3–2\n",
"plt.figure(figsize=(9, 9))\n",
"for idx, image_data in enumerate(X[:100]):\n",
" plt.subplot(10, 10, idx + 1)\n",
@ -427,7 +427,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code also computes the precision: TP / (FP + TP)\n",
"# extra code – this cell also computes the precision: TP / (FP + TP)\n",
"cm[1, 1] / (cm[0, 1] + cm[1, 1])"
]
},
@ -446,7 +446,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code also computes the recall: TP / (FN + TP)\n",
"# extra code – this cell also computes the recall: TP / (FN + TP)\n",
"cm[1, 1] / (cm[1, 0] + cm[1, 1])"
]
},
@ -467,7 +467,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code also computes the f1 score\n",
"# extra code – this cell also computes the f1 score\n",
"cm[1, 1] / (cm[1, 1] + (cm[1, 0] + cm[0, 1]) / 2)"
]
},
@ -513,8 +513,8 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code just shows that y_scores > 0 produces the same\n",
"# result as calling predict()\n",
"# extra code – just shows that y_scores > 0 produces the same result as\n",
"# calling predict()\n",
"y_scores > 0"
]
},
@ -556,12 +556,12 @@
"metadata": {},
"outputs": [],
"source": [
"plt.figure(figsize=(8, 4)) # not in the book – it's not needed, just formatting\n",
"plt.figure(figsize=(8, 4)) # extra code – it's not needed, just formatting\n",
"plt.plot(thresholds, precisions[:-1], \"b--\", label=\"Precision\", linewidth=2)\n",
"plt.plot(thresholds, recalls[:-1], \"g-\", label=\"Recall\", linewidth=2)\n",
"plt.vlines(threshold, 0, 1.0, \"k\", \"dotted\", label=\"threshold\")\n",
"\n",
"# not in the book – this section just beautifies and saves Figure 3–5\n",
"# extra code – this section just beautifies and saves Figure 3–5\n",
"idx = (thresholds >= threshold).argmax() # first index ≥ threshold\n",
"plt.plot(thresholds[idx], precisions[idx], \"bo\")\n",
"plt.plot(thresholds[idx], recalls[idx], \"go\")\n",
@ -580,13 +580,13 @@
"metadata": {},
"outputs": [],
"source": [
"import matplotlib.patches as patches # not in the book – for the curved arrow\n",
"import matplotlib.patches as patches # extra code – for the curved arrow\n",
"\n",
"plt.figure(figsize=(6, 5)) # not in the book – not needed, just formatting\n",
"plt.figure(figsize=(6, 5)) # extra code – not needed, just formatting\n",
"\n",
"plt.plot(recalls, precisions, linewidth=2, label=\"Precision/Recall curve\")\n",
"\n",
"# not in the book – just beautifies and saves Figure 3–6\n",
"# extra code – just beautifies and saves Figure 3–6\n",
"plt.plot([recalls[idx], recalls[idx]], [0., precisions[idx]], \"k:\")\n",
"plt.plot([0.0, recalls[idx]], [precisions[idx], precisions[idx]], \"k:\")\n",
"plt.plot([recalls[idx]], [precisions[idx]], \"ko\",\n",
@ -673,12 +673,12 @@
"idx_for_threshold_at_90 = (thresholds <= threshold_for_90_precision).argmax()\n",
"tpr_90, fpr_90 = tpr[idx_for_threshold_at_90], fpr[idx_for_threshold_at_90]\n",
"\n",
"plt.figure(figsize=(6, 5)) # not in the book – not needed, just formatting\n",
"plt.figure(figsize=(6, 5)) # extra code – not needed, just formatting\n",
"plt.plot(fpr, tpr, linewidth=2, label=\"ROC curve\")\n",
"plt.plot([0, 1], [0, 1], 'k:', label=\"Random classifier's ROC curve\")\n",
"plt.plot([fpr_90], [tpr_90], \"ko\", label=\"Threshold for 90% precision\")\n",
"\n",
"# not in the book – just beautifies and saves Figure 3–7\n",
"# extra code – just beautifies and saves Figure 3–7\n",
"plt.gca().add_patch(patches.FancyArrowPatch(\n",
" (0.20, 0.89), (0.07, 0.70),\n",
" connectionstyle=\"arc3,rad=.4\",\n",
@ -778,13 +778,13 @@
"metadata": {},
"outputs": [],
"source": [
"plt.figure(figsize=(6, 5)) # not in the book – not needed, just formatting\n",
"plt.figure(figsize=(6, 5)) # extra code – not needed, just formatting\n",
"\n",
"plt.plot(recalls_forest, precisions_forest, \"b-\", linewidth=2,\n",
" label=\"Random Forest\")\n",
"plt.plot(recalls, precisions, \"--\", linewidth=2, label=\"SGD\")\n",
"\n",
"# not in the book – just beautifies and saves Figure 3–8\n",
"# extra code – just beautifies and saves Figure 3–8\n",
"plt.xlabel(\"Recall\")\n",
"plt.ylabel(\"Precision\")\n",
"plt.axis([0, 1, 0, 1])\n",
@ -925,7 +925,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code shows how to get all 45 OvO scores if needed\n",
"# extra code – shows how to get all 45 OvO scores if needed\n",
"svm_clf.decision_function_shape = \"ovo\"\n",
"some_digit_scores_ovo = svm_clf.decision_function([some_digit])\n",
"some_digit_scores_ovo.round(2)"
@ -1033,7 +1033,7 @@
"from sklearn.metrics import ConfusionMatrixDisplay\n",
"\n",
"y_train_pred = cross_val_predict(sgd_clf, X_train_scaled, y_train, cv=3)\n",
"plt.rc('font', size=9) # not in the book – make the text smaller\n",
"plt.rc('font', size=9) # extra code – make the text smaller\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred)\n",
"plt.show()"
]
@ -1044,7 +1044,7 @@
"metadata": {},
"outputs": [],
"source": [
"plt.rc('font', size=10) # not in the book\n",
"plt.rc('font', size=10) # extra code\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred,\n",
" normalize=\"true\", values_format=\".0%\")\n",
"plt.show()"
@ -1057,7 +1057,7 @@
"outputs": [],
"source": [
"sample_weight = (y_train_pred != y_train)\n",
"plt.rc('font', size=10) # not in the book\n",
"plt.rc('font', size=10) # extra code\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred,\n",
" sample_weight=sample_weight,\n",
" normalize=\"true\", values_format=\".0%\")\n",
@ -1077,7 +1077,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates Figure 3–9\n",
"# extra code – this cell generates and saves Figure 3–9\n",
"fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(9, 4))\n",
"plt.rc('font', size=9)\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred, ax=axs[0])\n",
@ -1096,7 +1096,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates Figure 3–10\n",
"# extra code – this cell generates and saves Figure 3–10\n",
"fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(9, 4))\n",
"plt.rc('font', size=10)\n",
"ConfusionMatrixDisplay.from_predictions(y_train, y_train_pred, ax=axs[0],\n",
@ -1131,7 +1131,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates Figure 3–11\n",
"# extra code – this cell generates and saves Figure 3–11\n",
"size = 5\n",
"pad = 0.2\n",
"plt.figure(figsize=(size, size))\n",
@ -1224,9 +1224,9 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code shows that we get a negligible performance\n",
"# improvement when we set average=\"weighted\" because the\n",
"# classes are already pretty well balanced.\n",
"# extra code – shows that we get a negligible performance improvement when we\n",
"# set average=\"weighted\" because the classes are already pretty\n",
"# well balanced.\n",
"f1_score(y_multilabel, y_train_knn_pred, average=\"weighted\")"
]
},
@ -1279,7 +1279,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates Figure 3–12\n",
"# extra code – this cell generates and saves Figure 3–12\n",
"plt.subplot(121); plot_digit(X_test_mod[0])\n",
"plt.subplot(122); plot_digit(y_test_mod[0])\n",
"save_fig(\"noisy_digit_example_plot\")\n",
@ -1296,7 +1296,7 @@
"knn_clf.fit(X_train_mod, y_train_mod)\n",
"clean_digit = knn_clf.predict([X_test_mod[0]])\n",
"plot_digit(clean_digit)\n",
"save_fig(\"cleaned_digit_example_plot\") # not in the book – saves Figure 3–13\n",
"save_fig(\"cleaned_digit_example_plot\") # extra code – saves Figure 3–13\n",
"plt.show()"
]
},

221
04_training_linear_models.ipynb
View File

@ -154,7 +154,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – generates and saves Figure 4–1\n",
"# extra code – generates and saves Figure 4–1\n",
"\n",
"import matplotlib.pyplot as plt\n",
"\n",
@ -209,11 +209,11 @@
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"plt.figure(figsize=(6, 4)) # not in the book – not needed, just formatting\n",
"plt.figure(figsize=(6, 4)) # extra code – not needed, just formatting\n",
"plt.plot(X_new, y_predict, \"r-\", label=\"Predictions\")\n",
"plt.plot(X, y, \"b.\")\n",
"\n",
"# not in the book – beautifies and saves Figure 4–2\n",
"# extra code – beautifies and saves Figure 4–2\n",
"plt.xlabel(\"$x_1$\")\n",
"plt.ylabel(\"$y$\", rotation=0)\n",
"plt.axis([0, 2, 0, 15])\n",
@ -327,7 +327,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – generates and saves Figure 4–8\n",
"# extra code – generates and saves Figure 4–8\n",
"\n",
"import matplotlib as mpl\n",
"\n",
@ -381,8 +381,8 @@
"metadata": {},
"outputs": [],
"source": [
"theta_path_sgd = [] # not in the book – we need to store the path of theta in\n",
" # the parameter space to plot the next figure"
"theta_path_sgd = [] # extra code – we need to store the path of theta in the\n",
" # parameter space to plot the next figure"
]
},
{
@ -400,13 +400,13 @@
"np.random.seed(42)\n",
"theta = np.random.randn(2, 1) # random initialization\n",
"\n",
"n_shown = 20 # not in the book – just needed to generate the figure below\n",
"plt.figure(figsize=(6, 4)) # not in the book – not needed, just formatting\n",
"n_shown = 20 # extra code – just needed to generate the figure below\n",
"plt.figure(figsize=(6, 4)) # extra code – not needed, just formatting\n",
"\n",
"for epoch in range(n_epochs):\n",
" for iteration in range(m):\n",
"\n",
" # not in the book – these 4 lines are used to generate the figure\n",
" # extra code – these 4 lines are used to generate the figure\n",
" if epoch == 0 and iteration < n_shown:\n",
" y_predict = X_new_b @ theta\n",
" color = mpl.colors.rgb2hex(plt.cm.OrRd(iteration / n_shown + 0.15))\n",
@ -415,12 +415,12 @@
" random_index = np.random.randint(m)\n",
" xi = X_b[random_index : random_index + 1]\n",
" yi = y[random_index : random_index + 1]\n",
" gradients = 2 / 1 * xi.T @ (xi @ theta - yi)\n",
" gradients = 2 * xi.T @ (xi @ theta - yi) # for SGD, do not divide by m\n",
" eta = learning_schedule(epoch * m + iteration)\n",
" theta = theta - eta * gradients\n",
" theta_path_sgd.append(theta) # not in the book – to generate the figure\n",
" theta_path_sgd.append(theta) # extra code – to generate the figure\n",
"\n",
"# not in the book – this section beautifies and saves Figure 4–10\n",
"# extra code – this section beautifies and saves Figure 4–10\n",
"plt.plot(X, y, \"b.\")\n",
"plt.xlabel(\"$x_1$\")\n",
"plt.ylabel(\"$y$\", rotation=0)\n",
@ -449,9 +449,9 @@
"source": [
"from sklearn.linear_model import SGDRegressor\n",
"\n",
"sgd_reg = SGDRegressor(max_iter=1000, tol=1e-3, penalty=None, eta0=0.1,\n",
" random_state=42)\n",
"sgd_reg.fit(X, y.ravel()) # y.ravel() because fit() expects 1D targets"
"sgd_reg = SGDRegressor(max_iter=1000, tol=1e-5, penalty=None, eta0=0.01,\n",
" n_iter_no_change=100, random_state=42)\n",
"sgd_reg.fit(X, y.ravel()) # y.ravel() because fit() expects 1D targets\n"
]
},
{
@ -483,7 +483,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 4–11\n",
"# extra code – this cell generates and saves Figure 4–11\n",
"\n",
"from math import ceil\n",
"\n",
@ -558,7 +558,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 4–12\n",
"# extra code – this cell generates and saves Figure 4–12\n",
"plt.figure(figsize=(6, 4))\n",
"plt.plot(X, y, \"b.\")\n",
"plt.xlabel(\"$x_1$\")\n",
@ -608,7 +608,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 4–13\n",
"# extra code – this cell generates and saves Figure 4–13\n",
"\n",
"X_new = np.linspace(-3, 3, 100).reshape(100, 1)\n",
"X_new_poly = poly_features.transform(X_new)\n",
@ -632,7 +632,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 4–14\n",
"# extra code – this cell generates and saves Figure 4–14\n",
"\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.pipeline import make_pipeline\n",
@ -680,11 +680,11 @@
"train_errors = -train_scores.mean(axis=1)\n",
"valid_errors = -valid_scores.mean(axis=1)\n",
"\n",
"plt.figure(figsize=(6, 4)) # not in the book – not need, just formatting\n",
"plt.figure(figsize=(6, 4)) # extra code – not need, just formatting\n",
"plt.plot(train_sizes, train_errors, \"r-+\", linewidth=2, label=\"train\")\n",
"plt.plot(train_sizes, valid_errors, \"b-\", linewidth=3, label=\"valid\")\n",
"\n",
"# not in the book – beautifies and saves Figure 4–15\n",
"# extra code – beautifies and saves Figure 4–15\n",
"plt.xlabel(\"Training set size\")\n",
"plt.ylabel(\"RMSE\")\n",
"plt.grid()\n",
@ -718,7 +718,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – generates and saves Figure 4–16\n",
"# extra code – generates and saves Figure 4–16\n",
"\n",
"train_errors = -train_scores.mean(axis=1)\n",
"valid_errors = -valid_scores.mean(axis=1)\n",
@ -762,7 +762,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – we've done this type of generation several times before\n",
"# extra code – we've done this type of generation several times before\n",
"np.random.seed(42)\n",
"m = 20\n",
"X = 3 * np.random.rand(m, 1)\n",
@ -776,7 +776,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – a quick peek at the dataset we just generated\n",
"# extra code – a quick peek at the dataset we just generated\n",
"plt.figure(figsize=(6, 4))\n",
"plt.plot(X, y, \".\")\n",
"plt.xlabel(\"$x_1$\")\n",
@ -794,7 +794,7 @@
"source": [
"from sklearn.linear_model import Ridge\n",
"\n",
"ridge_reg = Ridge(alpha=1, solver=\"cholesky\")\n",
"ridge_reg = Ridge(alpha=0.1, solver=\"cholesky\")\n",
"ridge_reg.fit(X, y)\n",
"ridge_reg.predict([[1.5]])"
]
@ -805,7 +805,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 4–17\n",
"# extra code – this cell generates and saves Figure 4–17\n",
"\n",
"def plot_model(model_class, polynomial, alphas, **model_kargs):\n",
" plt.plot(X, y, \"b.\", linewidth=3)\n",
@ -845,8 +845,9 @@
"metadata": {},
"outputs": [],
"source": [
"sgd_reg = SGDRegressor(penalty=\"l2\", random_state=42)\n",
"sgd_reg.fit(X, y.ravel())\n",
"sgd_reg = SGDRegressor(penalty=\"l2\", alpha=0.1 / m, tol=None,\n",
" max_iter=1000, eta0=0.01, random_state=42)\n",
"sgd_reg.fit(X, y.ravel()) # y.ravel() because fit() expects 1D targets\n",
"sgd_reg.predict([[1.5]])"
]
},
@ -856,13 +857,36 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – show that we get roughly the same solution as earlier when\n",
"# extra code – show that we get roughly the same solution as earlier when\n",
"# we use Stochastic Average GD (solver=\"sag\")\n",
"ridge_reg = Ridge(alpha=1, solver=\"sag\", random_state=42)\n",
"ridge_reg = Ridge(alpha=0.1, solver=\"sag\", random_state=42)\n",
"ridge_reg.fit(X, y)\n",
"ridge_reg.predict([[1.5]])"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [],
"source": [
"# extra code – shows the closed form solution of Ridge regression,\n",
"# compare with the next Ridge model's learned parameters below\n",
"alpha = 0.1\n",
"A = np.array([[0., 0.], [0., 1.]])\n",
"X_b = np.c_[np.ones(m), X]\n",
"np.linalg.inv(X_b.T @ X_b + alpha * A) @ X_b.T @ y"
]
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {},
"outputs": [],
"source": [
"ridge_reg.intercept_, ridge_reg.coef_ # extra code"
]
},
{
"cell_type": "markdown",
"metadata": {},
@ -872,7 +896,7 @@
},
{
"cell_type": "code",
"execution_count": 40,
"execution_count": 42,
"metadata": {},
"outputs": [],
"source": [
@ -885,11 +909,11 @@
},
{
"cell_type": "code",
"execution_count": 41,
"execution_count": 43,
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 4–18\n",
"# extra code – this cell generates and saves Figure 4–18\n",
"plt.figure(figsize=(9, 3.5))\n",
"plt.subplot(121)\n",
"plot_model(Lasso, polynomial=False, alphas=(0, 0.1, 1), random_state=42)\n",
@ -903,11 +927,11 @@
},
{
"cell_type": "code",
"execution_count": 42,
"execution_count": 44,
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this BIG cell generates and saves Figure 4–19\n",
"# extra code – this BIG cell generates and saves Figure 4–19\n",
"\n",
"t1a, t1b, t2a, t2b = -1, 3, -1.5, 1.5\n",
"\n",
@ -996,7 +1020,7 @@
},
{
"cell_type": "code",
"execution_count": 43,
"execution_count": 45,
"metadata": {},
"outputs": [],
"source": [
@ -1023,22 +1047,7 @@
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this is the same code as earlier\n",
"np.random.seed(42)\n",
"m = 100\n",
"X = 6 * np.random.rand(m, 1) - 3\n",
"y = 0.5 * X ** 2 + X + 2 + np.random.randn(m, 1)\n",
"X_train, y_train = X[: m // 2], y[: m // 2, 0]\n",
"X_valid, y_valid = X[m // 2 :], y[m // 2 :, 0]"
]
},
{
"cell_type": "code",
"execution_count": 45,
"execution_count": 46,
"metadata": {},
"outputs": [],
"source": [
@ -1046,6 +1055,14 @@
"from sklearn.metrics import mean_squared_error\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"# extra code – creates the same quadratic dataset as earlier and splits it\n",
"np.random.seed(42)\n",
"m = 100\n",
"X = 6 * np.random.rand(m, 1) - 3\n",
"y = 0.5 * X ** 2 + X + 2 + np.random.randn(m, 1)\n",
"X_train, y_train = X[: m // 2], y[: m // 2, 0]\n",
"X_valid, y_valid = X[m // 2 :], y[m // 2 :, 0]\n",
"\n",
"preprocessing = make_pipeline(PolynomialFeatures(degree=90, include_bias=False),\n",
" StandardScaler())\n",
"X_train_prep = preprocessing.fit_transform(X_train)\n",
@ -1053,7 +1070,7 @@
"sgd_reg = SGDRegressor(penalty=None, eta0=0.002, random_state=42)\n",
"n_epochs = 500\n",
"best_valid_rmse = float('inf')\n",
"train_errors, val_errors = [], [] # not in the book – it's for the figure below\n",
"train_errors, val_errors = [], [] # extra code – it's for the figure below\n",
"\n",
"for epoch in range(n_epochs):\n",
" sgd_reg.partial_fit(X_train_prep, y_train)\n",
@ -1063,13 +1080,13 @@
" best_valid_rmse = val_error\n",
" best_model = deepcopy(sgd_reg)\n",
"\n",
" # not in the book – we evaluate the train error and save it for the figure\n",
" # extra code – we evaluate the train error and save it for the figure\n",
" y_train_predict = sgd_reg.predict(X_train_prep)\n",
" train_error = mean_squared_error(y_train, y_train_predict, squared=False)\n",
" val_errors.append(val_error)\n",
" train_errors.append(train_error)\n",
"\n",
"# not in the book – this section generates and saves Figure 4–20\n",
"# extra code – this section generates and saves Figure 4–20\n",
"best_epoch = np.argmin(val_errors)\n",
"plt.figure(figsize=(6, 4))\n",
"plt.annotate('Best model',\n",
@ -1106,11 +1123,11 @@
},
{
"cell_type": "code",
"execution_count": 46,
"execution_count": 47,
"metadata": {},
"outputs": [],
"source": [
"# not in the book – generates and saves Figure 4–21\n",
"# extra code – generates and saves Figure 4–21\n",
"\n",
"lim = 6\n",
"t = np.linspace(-lim, lim, 100)\n",
@ -1140,7 +1157,7 @@
},
{
"cell_type": "code",
"execution_count": 47,
"execution_count": 48,
"metadata": {},
"outputs": [],
"source": [
@ -1150,22 +1167,13 @@
"list(iris)"
]
},
{
"cell_type": "code",
"execution_count": 48,
"metadata": {},
"outputs": [],
"source": [
"print(iris.DESCR) # not in the book – it's a bit too long"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
"iris.data.head(3)"
"print(iris.DESCR) # extra code – it's a bit too long"
]
},
{
@ -1174,7 +1182,7 @@
"metadata": {},
"outputs": [],
"source": [
"iris.target.head(3) # note that the instances are not shuffled"
"iris.data.head(3)"
]
},
{
@ -1183,7 +1191,7 @@
"metadata": {},
"outputs": [],
"source": [
"iris.target_names"
"iris.target.head(3) # note that the instances are not shuffled"
]
},
{
@ -1191,6 +1199,15 @@
"execution_count": 52,
"metadata": {},
"outputs": [],
"source": [
"iris.target_names"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.model_selection import train_test_split\n",
@ -1205,7 +1222,7 @@
},
{
"cell_type": "code",
"execution_count": 53,
"execution_count": 54,
"metadata": {},
"outputs": [],
"source": [
@ -1213,14 +1230,14 @@
"y_proba = log_reg.predict_proba(X_new)\n",
"decision_boundary = X_new[y_proba[:, 1] >= 0.5][0, 0]\n",
"\n",
"plt.figure(figsize=(8, 3)) # not in the book – not needed, just formatting\n",
"plt.figure(figsize=(8, 3)) # extra code – not needed, just formatting\n",
"plt.plot(X_new, y_proba[:, 0], \"b--\", linewidth=2,\n",
" label=\"Not Iris virginica proba\")\n",
"plt.plot(X_new, y_proba[:, 1], \"g-\", linewidth=2, label=\"Iris virginica proba\")\n",
"plt.plot([decision_boundary, decision_boundary], [0, 1], \"k:\", linewidth=2,\n",
" label=\"Decision boundary\")\n",
"\n",
"# not in the book – this section beautifies and saves Figure 4–21\n",
"# extra code – this section beautifies and saves Figure 4–21\n",
"plt.arrow(x=decision_boundary, y=0.08, dx=-0.3, dy=0,\n",
" head_width=0.05, head_length=0.1, fc=\"b\", ec=\"b\")\n",
"plt.arrow(x=decision_boundary, y=0.92, dx=0.3, dy=0,\n",
@ -1239,7 +1256,7 @@
},
{
"cell_type": "code",
"execution_count": 54,
"execution_count": 55,
"metadata": {},
"outputs": [],
"source": [
@ -1248,7 +1265,7 @@
},
{
"cell_type": "code",
"execution_count": 55,
"execution_count": 56,
"metadata": {},
"outputs": [],
"source": [
@ -1257,11 +1274,11 @@
},
{
"cell_type": "code",
"execution_count": 56,
"execution_count": 57,
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 4–22\n",
"# extra code – this cell generates and saves Figure 4–22\n",
"\n",
"X = iris.data[[\"petal length (cm)\", \"petal width (cm)\"]].values\n",
"y = iris.target_names[iris.target] == 'virginica'\n",
@ -1307,7 +1324,7 @@
},
{
"cell_type": "code",
"execution_count": 57,
"execution_count": 58,
"metadata": {},
"outputs": [],
"source": [
@ -1321,7 +1338,7 @@
},
{
"cell_type": "code",
"execution_count": 58,
"execution_count": 59,
"metadata": {
"tags": []
},
@ -1332,7 +1349,7 @@
},
{
"cell_type": "code",
"execution_count": 59,
"execution_count": 60,
"metadata": {
"tags": []
},
@ -1343,11 +1360,11 @@
},
{
"cell_type": "code",
"execution_count": 60,
"execution_count": 61,
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 4–23\n",
"# extra code – this cell generates and saves Figure 4–23\n",
"\n",
"from matplotlib.colors import ListedColormap\n",
"\n",
@ -1419,7 +1436,7 @@
"metadata": {},
"source": [
"## 12. Batch Gradient Descent with early stopping for Softmax Regression\n",
"Exercise: _Implement Batch Gradient Descent with early stopping for Softmax Regression without using Scikit-Learn, only NumPy._"
"Exercise: _Implement Batch Gradient Descent with early stopping for Softmax Regression without using Scikit-Learn, only NumPy. Use it on a classification task such as the iris dataset._"
]
},
{
@ -1431,7 +1448,7 @@
},
{
"cell_type": "code",
"execution_count": 61,
"execution_count": 62,
"metadata": {},
"outputs": [],
"source": [
@ -1448,7 +1465,7 @@
},
{
"cell_type": "code",
"execution_count": 62,
"execution_count": 63,
"metadata": {},
"outputs": [],
"source": [
@ -1464,7 +1481,7 @@
},
{
"cell_type": "code",
"execution_count": 63,
"execution_count": 64,
"metadata": {},
"outputs": [],
"source": [
@ -1496,7 +1513,7 @@
},
{
"cell_type": "code",
"execution_count": 64,
"execution_count": 65,
"metadata": {},
"outputs": [],
"source": [
@ -1513,7 +1530,7 @@
},
{
"cell_type": "code",
"execution_count": 65,
"execution_count": 66,
"metadata": {},
"outputs": [],
"source": [
@ -1522,7 +1539,7 @@
},
{
"cell_type": "code",
"execution_count": 66,
"execution_count": 67,
"metadata": {},
"outputs": [],
"source": [
@ -1538,7 +1555,7 @@
},
{
"cell_type": "code",
"execution_count": 67,
"execution_count": 68,
"metadata": {},
"outputs": [],
"source": [
@ -1556,7 +1573,7 @@
},
{
"cell_type": "code",
"execution_count": 68,
"execution_count": 69,
"metadata": {},
"outputs": [],
"source": [
@ -1578,7 +1595,7 @@
},
{
"cell_type": "code",
"execution_count": 69,
"execution_count": 70,
"metadata": {},
"outputs": [],
"source": [
@ -1597,7 +1614,7 @@
},
{
"cell_type": "code",
"execution_count": 70,
"execution_count": 71,
"metadata": {},
"outputs": [],
"source": [
@ -1625,7 +1642,7 @@
},
{
"cell_type": "code",
"execution_count": 71,
"execution_count": 72,
"metadata": {},
"outputs": [],
"source": [
@ -1658,7 +1675,7 @@
},
{
"cell_type": "code",
"execution_count": 72,
"execution_count": 73,
"metadata": {},
"outputs": [],
"source": [
@ -1674,7 +1691,7 @@
},
{
"cell_type": "code",
"execution_count": 73,
"execution_count": 74,
"metadata": {},
"outputs": [],
"source": [
@ -1695,7 +1712,7 @@
},
{
"cell_type": "code",
"execution_count": 74,
"execution_count": 75,
"metadata": {},
"outputs": [],
"source": [
@ -1732,7 +1749,7 @@
},
{
"cell_type": "code",
"execution_count": 75,
"execution_count": 76,
"metadata": {},
"outputs": [],
"source": [
@ -1760,7 +1777,7 @@
},
{
"cell_type": "code",
"execution_count": 76,
"execution_count": 77,
"metadata": {},
"outputs": [],
"source": [
@ -1797,7 +1814,7 @@
},
{
"cell_type": "code",
"execution_count": 77,
"execution_count": 78,
"metadata": {},
"outputs": [],
"source": [
@ -1825,7 +1842,7 @@
},
{
"cell_type": "code",
"execution_count": 78,
"execution_count": 79,
"metadata": {},
"outputs": [],
"source": [
@ -1869,7 +1886,7 @@
},
{
"cell_type": "code",
"execution_count": 79,
"execution_count": 80,
"metadata": {},
"outputs": [],
"source": [

32
05_support_vector_machines.ipynb
View File

@ -140,7 +140,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–1\n",
"# extra code – this cell generates and saves Figure 5–1\n",
"\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
@ -219,7 +219,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–2\n",
"# extra code – this cell generates and saves Figure 5–2\n",
"\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
@ -269,7 +269,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–3\n",
"# extra code – this cell generates and saves Figure 5–3\n",
"\n",
"X_outliers = np.array([[3.4, 1.3], [3.2, 0.8]])\n",
"y_outliers = np.array([0, 0])\n",
@ -364,7 +364,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–4\n",
"# extra code – this cell generates and saves Figure 5–4\n",
"\n",
"scaler = StandardScaler()\n",
"svm_clf1 = LinearSVC(C=1, max_iter=10_000, random_state=42)\n",
@ -432,7 +432,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–5\n",
"# extra code – this cell generates and saves Figure 5–5\n",
"\n",
"X1D = np.linspace(-4, 4, 9).reshape(-1, 1)\n",
"X2D = np.c_[X1D, X1D**2]\n",
@ -492,7 +492,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–6\n",
"# extra code – this cell generates and saves Figure 5–6\n",
"\n",
"def plot_dataset(X, y, axes):\n",
" plt.plot(X[:, 0][y==0], X[:, 1][y==0], \"bs\")\n",
@ -545,7 +545,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–7\n",
"# extra code – this cell generates and saves Figure 5–7\n",
"\n",
"poly100_kernel_svm_clf = make_pipeline(\n",
" StandardScaler(),\n",
@ -585,7 +585,7 @@
},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–8\n",
"# extra code – this cell generates and saves Figure 5–8\n",
"\n",
"def gaussian_rbf(x, landmark, gamma):\n",
" return np.exp(-gamma * np.linalg.norm(x - landmark, axis=1)**2)\n",
@ -675,7 +675,7 @@
},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–9\n",
"# extra code – this cell generates and saves Figure 5–9\n",
"\n",
"from sklearn.svm import SVC\n",
"\n",
@ -724,7 +724,7 @@
"source": [
"from sklearn.svm import LinearSVR\n",
"\n",
"# not in the book – these 3 lines generate a simple linear dataset\n",
"# extra code – these 3 lines generate a simple linear dataset\n",
"np.random.seed(42)\n",
"X = 2 * np.random.rand(50, 1)\n",
"y = 4 + 3 * X[:, 0] + np.random.randn(50)\n",
@ -740,7 +740,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–10\n",
"# extra code – this cell generates and saves Figure 5–10\n",
"\n",
"def find_support_vectors(svm_reg, X, y):\n",
" y_pred = svm_reg.predict(X)\n",
@ -800,7 +800,7 @@
"source": [
"from sklearn.svm import SVR\n",
"\n",
"# not in the book – these 3 lines generate a simple quadratic dataset\n",
"# extra code – these 3 lines generate a simple quadratic dataset\n",
"np.random.seed(42)\n",
"X = 2 * np.random.rand(50, 1) - 1\n",
"y = 0.2 + 0.1 * X[:, 0] + 0.5 * X[:, 0] ** 2 + np.random.randn(50) / 10\n",
@ -816,7 +816,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–11\n",
"# extra code – this cell generates and saves Figure 5–11\n",
"\n",
"svm_poly_reg2 = make_pipeline(StandardScaler(),\n",
" SVR(kernel=\"poly\", degree=2, C=100))\n",
@ -857,7 +857,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–12\n",
"# extra code – this cell generates and saves Figure 5–12\n",
"\n",
"import matplotlib.patches as patches\n",
"\n",
@ -906,7 +906,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 5–13\n",
"# extra code – this cell generates and saves Figure 5–13\n",
"\n",
"s = np.linspace(-2.5, 2.5, 200)\n",
"hinge_pos = np.where(1 - s < 0, 0, 1 - s) # max(0, 1 - s)\n",
@ -1112,7 +1112,7 @@
"sgd_clf.fit(X, y)\n",
"\n",
"m = len(X)\n",
"t = np.array(y).reshape(-1, 1) * 2 - 1 # -1 if t==0, +1 if t==1\n",
"t = np.array(y).reshape(-1, 1) * 2 - 1 # -1 if y == 0, or +1 if y == 1\n",
"X_b = np.c_[np.ones((m, 1)), X] # Add bias input x0=1\n",
"X_b_t = X_b * t\n",
"sgd_theta = np.r_[sgd_clf.intercept_[0], sgd_clf.coef_[0]]\n",

20
06_decision_trees.ipynb
View File

@ -193,7 +193,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"!dot -Tpng {IMAGES_PATH / \"iris_tree.dot\"} -o {IMAGES_PATH / \"iris_tree.png\"}"
]
},
@ -213,7 +213,7 @@
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"\n",
"# not in the book – just formatting details\n",
"# extra code – just formatting details\n",
"from matplotlib.colors import ListedColormap\n",
"custom_cmap = ListedColormap(['#fafab0', '#9898ff', '#a0faa0'])\n",
"plt.figure(figsize=(8, 4))\n",
@ -226,7 +226,7 @@
" plt.plot(X_iris[:, 0][y_iris == idx], X_iris[:, 1][y_iris == idx],\n",
" style, label=f\"Iris {name}\")\n",
"\n",
"# not in the book – this section beautifies and saves Figure 6–2\n",
"# extra code – this section beautifies and saves Figure 6–2\n",
"tree_clf_deeper = DecisionTreeClassifier(max_depth=3, random_state=42)\n",
"tree_clf_deeper.fit(X_iris, y_iris)\n",
"th0, th1, th2a, th2b = tree_clf_deeper.tree_.threshold[[0, 2, 3, 6]]\n",
@ -341,7 +341,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 6–3\n",
"# extra code – this cell generates and saves Figure 6–3\n",
"\n",
"def plot_decision_boundary(clf, X, y, axes, cmap):\n",
" x1, x2 = np.meshgrid(np.linspace(axes[0], axes[1], 100),\n",
@ -437,7 +437,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – we've already seen how to use export_graphviz()\n",
"# extra code – we've already seen how to use export_graphviz()\n",
"export_graphviz(\n",
" tree_reg,\n",
" out_file=str(IMAGES_PATH / \"regression_tree.dot\"),\n",
@ -482,7 +482,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 6–5\n",
"# extra code – this cell generates and saves Figure 6–5\n",
"\n",
"def plot_regression_predictions(tree_reg, X, y, axes=[-0.5, 0.5, -0.05, 0.25]):\n",
" x1 = np.linspace(axes[0], axes[1], 500).reshape(-1, 1)\n",
@ -526,7 +526,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 6–6\n",
"# extra code – this cell generates and saves Figure 6–6\n",
"\n",
"tree_reg1 = DecisionTreeRegressor(random_state=42)\n",
"tree_reg2 = DecisionTreeRegressor(random_state=42, min_samples_leaf=10)\n",
@ -579,7 +579,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 6–7\n",
"# extra code – this cell generates and saves Figure 6–7\n",
"\n",
"np.random.seed(6)\n",
"X_square = np.random.rand(100, 2) - 0.5\n",
@ -630,7 +630,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 6–8\n",
"# extra code – this cell generates and saves Figure 6–8\n",
"\n",
"plt.figure(figsize=(8, 4))\n",
"\n",
@ -693,7 +693,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 6–9\n",
"# extra code – this cell generates and saves Figure 6–9\n",
"\n",
"plt.figure(figsize=(8, 4))\n",
"y_pred = tree_clf_tweaked.predict(X_iris_all).reshape(lengths.shape)\n",

22
07_ensemble_learning_and_random_forests.ipynb
View File

@ -133,7 +133,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 7–3\n",
"# extra code – this cell generates and saves Figure 7–3\n",
"\n",
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
@ -273,7 +273,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 7–5\n",
"# extra code – this cell generates and saves Figure 7–5\n",
"\n",
"def plot_decision_boundary(clf, X, y, alpha=1.0):\n",
" axes=[-1.5, 2.4, -1, 1.5]\n",
@ -363,7 +363,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code shows how to compute the 63% proba\n",
"# extra code – shows how to compute the 63% proba\n",
"print(1 - (1 - 1 / 1000) ** 1000)\n",
"print(1 - np.exp(-1))"
]
@ -413,7 +413,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code verifies that the predictions are identical\n",
"# extra code – verifies that the predictions are identical\n",
"bag_clf.fit(X_train, y_train)\n",
"y_pred_bag = bag_clf.predict(X_test)\n",
"np.all(y_pred_bag == y_pred_rf) # same predictions"
@ -447,7 +447,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 7–6\n",
"# extra code – this cell generates and saves Figure 7–6\n",
"\n",
"from sklearn.datasets import fetch_openml\n",
"\n",
@ -480,7 +480,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 7–8\n",
"# extra code – this cell generates and saves Figure 7–8\n",
"\n",
"m = len(X_train)\n",
"\n",
@ -534,7 +534,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – in case you're curious to see what the decision boundary\n",
"# extra code – in case you're curious to see what the decision boundary\n",
"# looks like for the AdaBoost classifier\n",
"plot_decision_boundary(ada_clf, X_train, y_train)"
]
@ -615,7 +615,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 7–9\n",
"# extra code – this cell generates and saves Figure 7–9\n",
"\n",
"def plot_predictions(regressors, X, y, axes, style,\n",
" label=None, data_style=\"b.\", data_label=None):\n",
@ -715,7 +715,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 7–10\n",
"# extra code – this cell generates and saves Figure 7–10\n",
"\n",
"fix, axes = plt.subplots(ncols=2, figsize=(10, 4), sharey=True)\n",
"\n",
@ -743,7 +743,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – at least not in this chapter, it's presented in chapter 2\n",
"# extra code – at least not in this chapter, it's presented in chapter 2\n",
"\n",
"import tarfile\n",
"import urllib.request\n",
@ -795,7 +795,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – evaluate the RMSE stats for the hgb_reg model\n",
"# extra code – evaluate the RMSE stats for the hgb_reg model\n",
"\n",
"from sklearn.model_selection import cross_val_score\n",
"\n",

32
08_dimensionality_reduction.ipynb
View File

@ -147,7 +147,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"\n",
"import numpy as np\n",
"from scipy.spatial.transform import Rotation\n",
@ -177,7 +177,7 @@
},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 8–2\n",
"# extra code – this cell generates and saves Figure 8–2\n",
"\n",
"import matplotlib.pyplot as plt\n",
"from mpl_toolkits.mplot3d import Axes3D\n",
@ -245,7 +245,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 8–3\n",
"# extra code – this cell generates and saves Figure 8–3\n",
"\n",
"fig = plt.figure()\n",
"ax = fig.add_subplot(1, 1, 1, aspect='equal')\n",
@ -281,7 +281,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 8–4\n",
"# extra code – this cell generates and saves Figure 8–4\n",
"\n",
"from matplotlib.colors import ListedColormap\n",
"\n",
@ -305,7 +305,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves plots for Figure 8–5\n",
"# extra code – this cell generates and saves plots for Figure 8–5\n",
"\n",
"plt.figure(figsize=(10, 4))\n",
"\n",
@ -332,7 +332,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves plots for Figure 8–6\n",
"# extra code – this cell generates and saves plots for Figure 8–6\n",
" \n",
"axes = [-11.5, 14, -2, 23, -12, 15]\n",
"x2s = np.linspace(axes[2], axes[3], 10)\n",
@ -404,7 +404,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 8–7\n",
"# extra code – this cell generates and saves Figure 8–7\n",
"\n",
"angle = np.pi / 5\n",
"stretch = 5\n",
@ -507,7 +507,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code shows how to construct Σ from s\n",
"# extra code – shows how to construct Σ from s\n",
"m, n = X.shape\n",
"Σ = np.zeros_like(X_centered)\n",
"Σ[:n, :n] = np.diag(s)\n",
@ -616,7 +616,7 @@
"metadata": {},
"outputs": [],
"source": [
"1 - pca.explained_variance_ratio_.sum() # not in the book"
"1 - pca.explained_variance_ratio_.sum() # extra code"
]
},
{
@ -678,7 +678,7 @@
"metadata": {},
"outputs": [],
"source": [
"pca.explained_variance_ratio_.sum() # not in the book"
"pca.explained_variance_ratio_.sum() # extra code"
]
},
{
@ -795,7 +795,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 8–9\n",
"# extra code – this cell generates and saves Figure 8–9\n",
"\n",
"plt.figure(figsize=(7, 4))\n",
"for idx, X in enumerate((X_train[::2100], X_recovered[::2100])):\n",
@ -929,7 +929,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – show the equation computed by johnson_lindenstrauss_min_dim\n",
"# extra code – show the equation computed by johnson_lindenstrauss_min_dim\n",
"d = int(4 * np.log(m) / (ε ** 2 / 2 - ε ** 3 / 3))\n",
"d"
]
@ -983,7 +983,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – performance comparison between Gaussian and Sparse RP\n",
"# extra code – performance comparison between Gaussian and Sparse RP\n",
"\n",
"from sklearn.random_projection import SparseRandomProjection\n",
"\n",
@ -1027,7 +1027,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 8–10\n",
"# extra code – this cell generates and saves Figure 8–10\n",
"\n",
"plt.scatter(X_unrolled[:, 0], X_unrolled[:, 1],\n",
" c=t, cmap=darker_hot)\n",
@ -1047,7 +1047,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – shows how well correlated z1 is to t: LLE worked fine\n",
"# extra code – shows how well correlated z1 is to t: LLE worked fine\n",
"plt.title(\"$z_1$ vs $t$\")\n",
"plt.scatter(X_unrolled[:, 0], t, c=t, cmap=darker_hot)\n",
"plt.xlabel(\"$z_1$\")\n",
@ -1099,7 +1099,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 8–11\n",
"# extra code – this cell generates and saves Figure 8–11\n",
"\n",
"titles = [\"MDS\", \"Isomap\", \"t-SNE\"]\n",
"\n",

80
09_unsupervised_learning.ipynb
View File

@ -147,7 +147,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–1\n",
"# extra code – this cell generates and saves Figure 9–1\n",
"\n",
"import matplotlib.pyplot as plt\n",
"from sklearn.datasets import load_iris\n",
@ -192,7 +192,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"\n",
"import numpy as np\n",
"from scipy import stats\n",
@ -263,7 +263,7 @@
"from sklearn.cluster import KMeans\n",
"from sklearn.datasets import make_blobs\n",
"\n",
"# not in the book – the exact arguments of make_blobs() are not important\n",
"# extra code – the exact arguments of make_blobs() are not important\n",
"blob_centers = np.array([[ 0.2, 2.3], [-1.5 , 2.3], [-2.8, 1.8],\n",
" [-2.8, 2.8], [-2.8, 1.3]])\n",
"blob_std = np.array([0.4, 0.3, 0.1, 0.1, 0.1])\n",
@ -288,7 +288,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–2\n",
"# extra code – this cell generates and saves Figure 9–2\n",
"\n",
"def plot_clusters(X, y=None):\n",
" plt.scatter(X[:, 0], X[:, 1], c=y, s=1)\n",
@ -399,7 +399,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–3\n",
"# extra code – this cell generates and saves Figure 9–3\n",
"\n",
"def plot_data(X):\n",
" plt.plot(X[:, 0], X[:, 1], 'k.', markersize=2)\n",
@ -489,7 +489,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"np.linalg.norm(np.tile(X_new, (1, k)).reshape(-1, k, 2)\n",
" - kmeans.cluster_centers_, axis=2).round(2)"
]
@ -532,7 +532,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–4\n",
"# extra code – this cell generates and saves Figure 9–4\n",
"\n",
"kmeans_iter1 = KMeans(n_clusters=5, init=\"random\", n_init=1, max_iter=1,\n",
" random_state=5)\n",
@ -600,7 +600,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–5\n",
"# extra code – this cell generates and saves Figure 9–5\n",
"\n",
"def plot_clusterer_comparison(clusterer1, clusterer2, X, title1=None,\n",
" title2=None):\n",
@ -647,7 +647,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"plt.figure(figsize=(8, 4))\n",
"plot_decision_boundaries(kmeans, X)"
]
@ -681,7 +681,7 @@
"metadata": {},
"outputs": [],
"source": [
"kmeans_rnd_init1.inertia_ # not in the book"
"kmeans_rnd_init1.inertia_ # extra code"
]
},
{
@ -690,7 +690,7 @@
"metadata": {},
"outputs": [],
"source": [
"kmeans_rnd_init2.inertia_ # not in the book"
"kmeans_rnd_init2.inertia_ # extra code"
]
},
{
@ -706,7 +706,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"X_dist = kmeans.transform(X)\n",
"(X_dist[np.arange(len(X_dist)), kmeans.labels_] ** 2).sum()"
]
@ -754,7 +754,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"kmeans_rnd_10_inits = KMeans(n_clusters=5, init=\"random\", n_init=10,\n",
" random_state=2)\n",
"kmeans_rnd_10_inits.fit(X)"
@ -773,7 +773,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"plt.figure(figsize=(8, 4))\n",
"plot_decision_boundaries(kmeans_rnd_10_inits, X)\n",
"plt.show()"
@ -964,7 +964,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–6\n",
"# extra code – this cell generates and saves Figure 9–6\n",
"\n",
"from timeit import timeit\n",
"\n",
@ -1024,7 +1024,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–7\n",
"# extra code – this cell generates and saves Figure 9–7\n",
"\n",
"kmeans_k3 = KMeans(n_clusters=3, random_state=42)\n",
"kmeans_k8 = KMeans(n_clusters=8, random_state=42)\n",
@ -1072,7 +1072,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–8\n",
"# extra code – this cell generates and saves Figure 9–8\n",
"\n",
"kmeans_per_k = [KMeans(n_clusters=k, random_state=42).fit(X)\n",
" for k in range(1, 10)]\n",
@ -1104,7 +1104,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"plot_decision_boundaries(kmeans_per_k[4 - 1], X)\n",
"plt.show()"
]
@ -1147,7 +1147,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–9\n",
"# extra code – this cell generates and saves Figure 9–9\n",
"\n",
"silhouette_scores = [silhouette_score(X, model.labels_)\n",
" for model in kmeans_per_k[1:]]\n",
@ -1182,7 +1182,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–10\n",
"# extra code – this cell generates and saves Figure 9–10\n",
"\n",
"from sklearn.metrics import silhouette_samples\n",
"from matplotlib.ticker import FixedLocator, FixedFormatter\n",
@ -1253,7 +1253,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–11\n",
"# extra code – this cell generates and saves Figure 9–11\n",
"\n",
"X1, y1 = make_blobs(n_samples=1000, centers=((4, -4), (0, 0)), random_state=42)\n",
"X1 = X1.dot(np.array([[0.374, 0.95], [0.732, 0.598]]))\n",
@ -1303,7 +1303,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"\n",
"root = \"https://raw.githubusercontent.com/ageron/handson-ml3/main/\"\n",
"filename = \"ladybug.png\"\n",
@ -1344,7 +1344,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–12\n",
"# extra code – this cell generates and saves Figure 9–12\n",
"\n",
"segmented_imgs = []\n",
"n_colors = (10, 8, 6, 4, 2)\n",
@ -1367,7 +1367,7 @@
" plt.title(f\"{n_clusters} colors\")\n",
" plt.axis('off')\n",
"\n",
"save_fig('image_segmentation_diagram', tight_layout=False)\n",
"save_fig('image_segmentation_plot', tight_layout=False)\n",
"plt.show()"
]
},
@ -1440,7 +1440,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – measure the accuracy when we use the whole training set\n",
"# extra code – measure the accuracy when we use the whole training set\n",
"log_reg_full = LogisticRegression(max_iter=10_000)\n",
"log_reg_full.fit(X_train, y_train)\n",
"log_reg_full.score(X_test, y_test)"
@ -1479,7 +1479,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 9–13\n",
"# extra code – this cell generates and saves Figure 9–13\n",
"\n",
"plt.figure(figsize=(8, 2))\n",
"for index, X_representative_digit in enumerate(X_representative_digits):\n",
@ -1488,7 +1488,7 @@
" interpolation=\"bilinear\")\n",
" plt.axis('off')\n",
"\n",
"save_fig(\"representative_images_diagram\", tight_layout=False)\n",
"save_fig(\"representative_images_plot\", tight_layout=False)\n",
"plt.show()"
]
},
@ -1694,7 +1694,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 9–14\n",
"# extra code – this cell generates and saves Figure 9–14\n",
"\n",
"def plot_dbscan(dbscan, X, size, show_xlabels=True, show_ylabels=True):\n",
" core_mask = np.zeros_like(dbscan.labels_, dtype=bool)\n",
@ -1747,7 +1747,7 @@
"metadata": {},
"outputs": [],
"source": [
"dbscan = dbscan2 # not in the book – the text says we now use eps=0.2"
"dbscan = dbscan2 # extra code – the text says we now use eps=0.2"
]
},
{
@ -1787,7 +1787,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 9–15\n",
"# extra code – this cell generates and saves Figure 9–15\n",
"\n",
"plt.figure(figsize=(6, 3))\n",
"plot_decision_boundaries(knn, X, show_centroids=False)\n",
@ -2172,7 +2172,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – bonus material\n",
"# extra code – bonus material\n",
"\n",
"resolution = 100\n",
"grid = np.arange(-10, 10, 1 / resolution)\n",
@ -2197,7 +2197,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cells generates and saves Figure 9–16\n",
"# extra code – this cells generates and saves Figure 9–16\n",
"\n",
"from matplotlib.colors import LogNorm\n",
"\n",
@ -2256,7 +2256,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–17\n",
"# extra code – this cell generates and saves Figure 9–17\n",
"\n",
"gm_full = GaussianMixture(n_components=3, n_init=10,\n",
" covariance_type=\"full\", random_state=42)\n",
@ -2294,7 +2294,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – comparing covariance_type=\"full\" and covariance_type=\"diag\"\n",
"# extra code – comparing covariance_type=\"full\" and covariance_type=\"diag\"\n",
"compare_gaussian_mixtures(gm_full, gm_diag, X)\n",
"plt.tight_layout()\n",
"plt.show()"
@ -2331,7 +2331,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 9–18\n",
"# extra code – this cell generates and saves Figure 9–18\n",
"\n",
"plt.figure(figsize=(8, 4))\n",
"\n",
@ -2373,7 +2373,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 9–19\n",
"# extra code – this cell generates and saves Figure 9–19\n",
"\n",
"from scipy.stats import norm\n",
"\n",
@ -2479,7 +2479,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – bonus material\n",
"# extra code – bonus material\n",
"n_clusters = 3\n",
"n_dims = 2\n",
"n_params_for_weights = n_clusters - 1\n",
@ -2514,7 +2514,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 9–20\n",
"# extra code – this cell generates and saves Figure 9–20\n",
"\n",
"gms_per_k = [GaussianMixture(n_components=k, n_init=10, random_state=42).fit(X)\n",
" for k in range(1, 11)]\n",
@ -2576,7 +2576,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this figure is almost identical to Figure 9–16\n",
"# extra code – this figure is almost identical to Figure 9–16\n",
"plt.figure(figsize=(8, 5))\n",
"plot_gaussian_mixture(bgm, X)\n",
"plt.show()"
@ -2588,7 +2588,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 9–21\n",
"# extra code – this cell generates and saves Figure 9–21\n",
"\n",
"X_moons, y_moons = make_moons(n_samples=1000, noise=0.05, random_state=42)\n",
"\n",

60
10_neural_nets_with_keras.ipynb
View File

@ -77,7 +77,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"And TensorFlow ≥ 2.6:"
"And TensorFlow ≥ 2.7:"
]
},
{
@ -88,7 +88,7 @@
"source": [
"import tensorflow as tf\n",
"\n",
"assert tf.__version__ >= \"2.6.0\""
"assert tf.__version__ >= \"2.7.0\""
]
},
{
@ -189,7 +189,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – extra material\n",
"# extra code – shows how to build and train a Perceptron\n",
"\n",
"from sklearn.linear_model import SGDClassifier\n",
"\n",
@ -213,7 +213,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – extra material\n",
"# extra code – plots the decision boundary of a Perceptron on the iris dataset\n",
"\n",
"import matplotlib.pyplot as plt\n",
"from matplotlib.colors import ListedColormap\n",
@ -256,7 +256,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code generates and saves Figure 10–8\n",
"# extra code – this cell generates and saves Figure 10–8\n",
"\n",
"from scipy.special import expit as sigmoid\n",
"\n",
@ -358,7 +358,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this was left as an exercise for the reader\n",
"# extra code – this was left as an exercise for the reader\n",
"\n",
"from sklearn.datasets import load_iris\n",
"from sklearn.model_selection import train_test_split\n",
@ -470,7 +470,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"\n",
"plt.imshow(X_train[0], cmap=\"binary\")\n",
"plt.axis('off')\n",
@ -539,7 +539,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 10–10\n",
"# extra code – this cell generates and saves Figure 10–10\n",
"\n",
"n_rows = 4\n",
"n_cols = 10\n",
@ -585,7 +585,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – clear the session to reset the name counters\n",
"# extra code – clear the session to reset the name counters\n",
"tf.keras.backend.clear_session()\n",
"tf.random.set_seed(42)\n",
"\n",
@ -612,7 +612,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – another way to display the model's architecture\n",
"# extra code – another way to display the model's architecture\n",
"tf.keras.utils.plot_model(model, \"my_fashion_mnist_model.png\", show_shapes=True)"
]
},
@ -712,7 +712,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell is equivalent to the previous cell\n",
"# extra code – this cell is equivalent to the previous cell\n",
"model.compile(loss=tf.keras.losses.sparse_categorical_crossentropy,\n",
" optimizer=tf.keras.optimizers.SGD(),\n",
" metrics=[tf.keras.metrics.sparse_categorical_accuracy])"
@ -724,7 +724,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code shows how to convert class ids to one-hot vectors\n",
"# extra code – shows how to convert class ids to one-hot vectors\n",
"tf.keras.utils.to_categorical([0, 5, 1, 0], num_classes=10)"
]
},
@ -741,7 +741,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this code shows how to convert one-hot vectors to class ids\n",
"# extra code – shows how to convert one-hot vectors to class ids\n",
"np.argmax(\n",
" [[1., 0., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
" [0., 0., 0., 0., 0., 1., 0., 0., 0., 0.],\n",
@ -798,8 +798,8 @@
"pd.DataFrame(history.history).plot(\n",
" figsize=(8, 5), xlim=[0, 29], ylim=[0, 1], grid=True, xlabel=\"Epoch\",\n",
" style=[\"r--\", \"r--.\", \"b-\", \"b-*\"])\n",
"plt.legend(loc=\"lower left\") # not in the book\n",
"save_fig(\"keras_learning_curves_plot\") # not in the book\n",
"plt.legend(loc=\"lower left\") # extra code\n",
"save_fig(\"keras_learning_curves_plot\") # extra code\n",
"plt.show()"
]
},
@ -809,7 +809,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – shows how to shift the training curve by -1/2 epoch\n",
"# extra code – shows how to shift the training curve by -1/2 epoch\n",
"plt.figure(figsize=(8, 5))\n",
"for key, style in zip(history.history, [\"r--\", \"r--.\", \"b-\", \"b-*\"]):\n",
" epochs = np.array(history.epoch) + (0 if key.startswith(\"val_\") else -0.5)\n",
@ -883,7 +883,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – this cell generates and saves Figure 10–12\n",
"# extra code – this cell generates and saves Figure 10–12\n",
"plt.figure(figsize=(7.2, 2.4))\n",
"for index, image in enumerate(X_new):\n",
" plt.subplot(1, 3, index + 1)\n",
@ -915,7 +915,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – load and split the California housing dataset, like earlier\n",
"# extra code – load and split the California housing dataset, like earlier\n",
"housing = fetch_california_housing()\n",
"X_train_full, X_test, y_train_full, y_test = train_test_split(\n",
" housing.data, housing.target, random_state=42)\n",
@ -986,7 +986,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – reset the name counters and make the code reproducible\n",
"# extra code – reset the name counters and make the code reproducible\n",
"tf.keras.backend.clear_session()\n",
"tf.random.set_seed(42)"
]
@ -1050,7 +1050,7 @@
"metadata": {},
"outputs": [],
"source": [
"tf.random.set_seed(42) # not in the book"
"tf.random.set_seed(42) # extra code"
]
},
{
@ -1220,7 +1220,7 @@
" aux_output = self.aux_output(hidden2)\n",
" return output, aux_output\n",
"\n",
"tf.random.set_seed(42) # not in the book – just for reproducibility\n",
"tf.random.set_seed(42) # extra code – just for reproducibility\n",
"model = WideAndDeepModel(30, activation=\"relu\", name=\"my_cool_model\")"
]
},
@ -1256,7 +1256,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – delete the directory, in case it already exists\n",
"# extra code – delete the directory, in case it already exists\n",
"\n",
"import shutil\n",
"\n",
@ -1278,7 +1278,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – show the contents of the my_keras_model/ directory\n",
"# extra code – show the contents of the my_keras_model/ directory\n",
"for path in sorted(Path(\"my_keras_model\").glob(\"**/*\")):\n",
" print(path)"
]
@ -1317,7 +1317,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – show the list of my_weights.* files\n",
"# extra code – show the list of my_weights.* files\n",
"for path in sorted(Path().glob(\"my_weights.*\")):\n",
" print(path)"
]
@ -1335,7 +1335,7 @@
"metadata": {},
"outputs": [],
"source": [
"shutil.rmtree(\"my_checkpoints\", ignore_errors=True) # not in the book"
"shutil.rmtree(\"my_checkpoints\", ignore_errors=True) # extra code"
]
},
{
@ -1411,7 +1411,7 @@
"metadata": {},
"outputs": [],
"source": [
"if \"google.colab\" in sys.modules: # not in the book\n",
"if \"google.colab\" in sys.modules: # extra code\n",
" %pip install -q -U tensorboard-plugin-profile"
]
},
@ -1447,7 +1447,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – builds the first regression model we used earlier\n",
"# extra code – builds the first regression model we used earlier\n",
"tf.keras.backend.clear_session()\n",
"tf.random.set_seed(42)\n",
"norm_layer = tf.keras.layers.Normalization(input_shape=X_train.shape[1:])\n",
@ -1516,7 +1516,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"\n",
"if \"google.colab\" in sys.modules:\n",
" from google.colab import output\n",
@ -1574,7 +1574,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book\n",
"# extra code\n",
"\n",
"if \"google.colab\" in sys.modules:\n",
" !tensorboard dev upload --logdir ./my_logs --one_shot \\\n",
@ -1632,7 +1632,7 @@
"metadata": {},
"outputs": [],
"source": [
"# not in the book – extra material\n",
"# extra code – lists all running TensorBoard server instances\n",
"\n",
"from tensorboard import notebook\n",
"\n",