Add some section headers
Aurélien Geron
parent
2bd68d6348
commit
6b821335c0
|
|
@ -83,7 +83,14 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Get the data"
|
||||
"# Get the Data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Download the Data"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -132,6 +139,13 @@
|
|||
" return pd.read_csv(csv_path)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Take a Quick Look at the Data Structure"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
|
|
@ -182,6 +196,13 @@
|
|||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Create a Test Set"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
|
|
@ -443,7 +464,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Discover and visualize the data to gain insights"
|
||||
"# Discover and Visualize the Data to Gain Insights"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -455,6 +476,13 @@
|
|||
"housing = strat_train_set.copy()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Visualizing Geographical Data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 33,
|
||||
|
|
@ -540,6 +568,13 @@
|
|||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Looking for Correlations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 38,
|
||||
|
|
@ -585,6 +620,13 @@
|
|||
"save_fig(\"income_vs_house_value_scatterplot\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Experimenting with Attribute Combinations"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 42,
|
||||
|
|
@ -631,7 +673,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Prepare the data for Machine Learning algorithms"
|
||||
"# Prepare the Data for Machine Learning Algorithms"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -644,6 +686,29 @@
|
|||
"housing_labels = strat_train_set[\"median_house_value\"].copy()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Data Cleaning"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In the book 3 options are listed:\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"housing.dropna(subset=[\"total_bedrooms\"]) # option 1\n",
|
||||
"housing.drop(\"total_bedrooms\", axis=1) # option 2\n",
|
||||
"median = housing[\"total_bedrooms\"].median() # option 3\n",
|
||||
"housing[\"total_bedrooms\"].fillna(median, inplace=True)\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"To demonstrate each of them, let's create a copy of the housing dataset, but keeping only the rows that contain at least one null. Then it will be easier to visualize exactly what each option does:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 47,
|
||||
|
|
@ -815,6 +880,13 @@
|
|||
"housing_tr.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Handling Text and Categorical Attributes"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
|
|
@ -910,6 +982,13 @@
|
|||
"cat_encoder.categories_"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Custom Transformers"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
|
|
@ -985,6 +1064,13 @@
|
|||
"housing_extra_attribs.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Transformation Pipelines"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
|
|
@ -1154,7 +1240,14 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Select and train a model "
|
||||
"# Select and Train a Model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Training and Evaluating on the Training Set"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -1269,7 +1362,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Fine-tune your model"
|
||||
"## Better Evaluation Using Cross-Validation"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -1382,6 +1475,20 @@
|
|||
"svm_rmse"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Fine-Tune Your Model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Grid Search"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 99,
|
||||
|
|
@ -1457,6 +1564,13 @@
|
|||
"pd.DataFrame(grid_search.cv_results_)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Randomized Search"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 104,
|
||||
|
|
@ -1488,6 +1602,13 @@
|
|||
" print(np.sqrt(-mean_score), params)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Analyze the Best Models and Their Errors"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 106,
|
||||
|
|
@ -1512,6 +1633,13 @@
|
|||
"sorted(zip(feature_importances, attributes), reverse=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Evaluate Your System on the Test Set"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 108,
|
||||
|
|
|
|||
|
|
@ -245,7 +245,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Binary classifier"
|
||||
"# Training a Binary Classifier"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -296,6 +296,20 @@
|
|||
"cross_val_score(sgd_clf, X_train, y_train_5, cv=3, scoring=\"accuracy\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Performance Measures"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Measuring Accuracy Using Cross-Validation"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
|
|
@ -362,6 +376,13 @@
|
|||
"* lastly, other things may prevent perfect reproducibility, such as Python dicts and sets whose order is not guaranteed to be stable across sessions, or the order of files in a directory which is also not guaranteed."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Confusion Matrix"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
|
|
@ -394,6 +415,13 @@
|
|||
"confusion_matrix(y_train_5, y_train_perfect_predictions)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Precision and Recall"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
|
|
@ -453,6 +481,13 @@
|
|||
"cm[1, 1] / (cm[1, 1] + (cm[1, 0] + cm[0, 1]) / 2)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Precision/Recall Trade-off"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 30,
|
||||
|
|
@ -625,7 +660,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ROC curves"
|
||||
"## The ROC Curve"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -757,7 +792,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Multiclass classification"
|
||||
"# Multiclass Classification"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -882,7 +917,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Error analysis"
|
||||
"# Error Analysis"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -969,7 +1004,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Multilabel classification"
|
||||
"# Multilabel Classification"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -1018,7 +1053,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Multioutput classification"
|
||||
"# Multioutput Classification"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**Chapter 4 – Training Linear Models**"
|
||||
"**Chapter 4 – Training Models**"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -89,7 +89,14 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Linear regression using the Normal Equation"
|
||||
"# Linear Regression"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## The Normal Equation"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -243,7 +250,8 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Linear regression using batch gradient descent"
|
||||
"# Gradient Descent\n",
|
||||
"## Batch Gradient Descent"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -330,7 +338,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Stochastic Gradient Descent"
|
||||
"## Stochastic Gradient Descent"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -416,7 +424,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Mini-batch gradient descent"
|
||||
"## Mini-batch gradient descent"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -494,7 +502,7 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Polynomial regression"
|
||||
"# Polynomial Regression"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -616,6 +624,13 @@
|
|||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Learning Curves"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 35,
|
||||
|
|
@ -678,7 +693,14 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Regularized models"
|
||||
"# Regularized Linear Models"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Ridge Regression"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -772,6 +794,13 @@
|
|||
"sgd_reg.predict([[1.5]])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Lasso Regression"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 43,
|
||||
|
|
@ -803,6 +832,13 @@
|
|||
"lasso_reg.predict([[1.5]])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Elastic Net"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 45,
|
||||
|
|
@ -815,6 +851,13 @@
|
|||
"elastic_net.predict([[1.5]])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Early Stopping"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 46,
|
||||
|
|
@ -829,13 +872,6 @@
|
|||
"X_train, X_val, y_train, y_val = train_test_split(X[:50], y[:50].ravel(), test_size=0.5, random_state=10)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Early stopping example:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 47,
|
||||
|
|
@ -1029,7 +1065,14 @@
|
|||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Logistic regression"
|
||||
"# Logistic Regression"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Decision Boundaries"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -1166,6 +1209,13 @@
|
|||
"log_reg.predict([[1.7], [1.5]])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Softmax Regression"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 62,
|
||||
|
|
|
|||
Loading…
Reference in New Issue