Pushing the docs for revision for branch: master, commit 317dea8a05b0087f83318f318d112976e90566ff

Author: sklearn-ci

dev/_downloads/document_clustering.py

@@ -27,7 +27,7 @@
 Two algorithms are demoed: ordinary k-means and its more scalable cousin
 minibatch k-means.
 
-Additionally, latent sematic analysis can also be used to reduce dimensionality
+Additionally, latent semantic analysis can also be used to reduce dimensionality
 and discover latent patterns in the data. 
 
 It can be noted that k-means (and minibatch k-means) are very sensitive to

dev/_downloads/plot_ard.py

@@ -32,7 +32,7 @@
 n_samples, n_features = 100, 100
 # Create Gaussian data
 X = np.random.randn(n_samples, n_features)
-# Create weigts with a precision lambda_ of 4.
+# Create weights with a precision lambda_ of 4.
 lambda_ = 4.
 w = np.zeros(n_features)
 # Only keep 10 weights of interest

dev/_downloads/plot_bayesian_ridge.py

@@ -25,11 +25,11 @@
 from sklearn.linear_model import BayesianRidge, LinearRegression
 
 ###############################################################################
-# Generating simulated data with Gaussian weigthts
+# Generating simulated data with Gaussian weights
 np.random.seed(0)
 n_samples, n_features = 100, 100
 X = np.random.randn(n_samples, n_features)  # Create Gaussian data
-# Create weigts with a precision lambda_ of 4.
+# Create weights with a precision lambda_ of 4.
 lambda_ = 4.
 w = np.zeros(n_features)
 # Only keep 10 weights of interest

dev/_downloads/plot_calibration_curve.py

@@ -125,10 +125,10 @@ def plot_calibration_curve(est, name, fig_index):
 
     plt.tight_layout()
 
-# Plot calibration cuve for Gaussian Naive Bayes
+# Plot calibration curve for Gaussian Naive Bayes
 plot_calibration_curve(GaussianNB(), "Naive Bayes", 1)
 
-# Plot calibration cuve for Linear SVC
+# Plot calibration curve for Linear SVC
 plot_calibration_curve(LinearSVC(), "SVC", 2)
 
 plt.show()

dev/_downloads/plot_compare_calibration.py

@@ -10,10 +10,10 @@
 0.8, approx. 80% actually belong to the positive class.
 
 LogisticRegression returns well calibrated predictions as it directly
-optimizes log-loss. In contrast, the other methods return biased probilities,
+optimizes log-loss. In contrast, the other methods return biased probabilities,
 with different biases per method:
 
-* GaussianNaiveBayes tends to push probabilties to 0 or 1 (note the counts in
+* GaussianNaiveBayes tends to push probabilities to 0 or 1 (note the counts in
   the histograms). This is mainly because it makes the assumption that features
   are conditionally independent given the class, which is not the case in this
   dataset which contains 2 redundant features.
@@ -35,7 +35,7 @@
   trained with random forests have relatively high variance due to feature
   subseting." As a result, the calibration curve shows a characteristic sigmoid
   shape, indicating that the classifier could trust its "intuition" more and
-  return probabilties closer to 0 or 1 typically.
+  return probabilities closer to 0 or 1 typically.
 
 * Support Vector Classification (SVC) shows an even more sigmoid curve as
   the  RandomForestClassifier, which is typical for maximum-margin methods

dev/_downloads/plot_compare_cross_decomposition.py

@@ -135,7 +135,7 @@
 y = X[:, 0] + 2 * X[:, 1] + np.random.normal(size=n * 1) + 5
 pls1 = PLSRegression(n_components=3)
 pls1.fit(X, y)
-# note that the number of compements exceeds 1 (the dimension of y)
+# note that the number of components exceeds 1 (the dimension of y)
 print("Estimated betas")
 print(np.round(pls1.coef_, 1))
 

dev/_downloads/plot_kernel_approximation.py

@@ -169,7 +169,7 @@
 
 X = pca.transform(data_train)
 
-# Gemerate grid along first two principal components
+# Generate grid along first two principal components
 multiples = np.arange(-2, 2, 0.1)
 # steps along first component
 first = multiples[:, np.newaxis] * pca.components_[0, :]

dev/_downloads/plot_kmeans_silhouette_analysis.py

@@ -9,7 +9,7 @@
 a way to assess parameters like number of clusters visually. This measure has a
 range of [-1, 1].
 
-Silhoette coefficients (as these values are referred to as) near +1 indicate
+Silhouette coefficients (as these values are referred to as) near +1 indicate
 that the sample is far away from the neighboring clusters. A value of 0
 indicates that the sample is on or very close to the decision boundary between
 two neighboring clusters and negative values indicate that those samples might
@@ -43,7 +43,7 @@
 print(__doc__)
 
 # Generating the sample data from make_blobs
-# This particular setting has one distict cluster and 3 clusters placed close
+# This particular setting has one distinct cluster and 3 clusters placed close
 # together.
 X, y = make_blobs(n_samples=500,
                   n_features=2,
@@ -110,7 +110,7 @@
     ax1.set_xlabel("The silhouette coefficient values")
     ax1.set_ylabel("Cluster label")
 
-    # The vertical line for average silhoutte score of all the values
+    # The vertical line for average silhouette score of all the values
     ax1.axvline(x=silhouette_avg, color="red", linestyle="--")
 
     ax1.set_yticks([])  # Clear the yaxis labels / ticks

dev/_downloads/plot_learning_curve.py

@@ -27,7 +27,7 @@
 def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
                         n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
     """
-    Generate a simple plot of the test and traning learning curve.
+    Generate a simple plot of the test and training learning curve.
 
     Parameters
     ----------

dev/_downloads/plot_mlp_alpha.py

@@ -13,7 +13,7 @@
 in a decision boundary plot that appears with lesser curvatures.
 Similarly, decreasing alpha may fix high bias (a sign of underfitting) by
 encouraging larger weights, potentially resulting in a more complicated
-decision boundery.
+decision boundary.
 """
 print(__doc__)