Intro to machine learning with scikit learn
Download as ppt, pdf1 like1,897 views
The document discusses machine learning concepts and programming with scikit-learn. It introduces the machine learning process of getting data, pre-processing, partitioning for training and testing, creating a classifier, training and evaluating the model. As an example, it loads the Iris dataset and plots sepal length vs width with labels. It also uses PCA for dimensionality reduction to better classify the Iris data in 3 dimensions.
![7
Data Partitioning
โข Data and labels
โ{[data], [labels]}
โ{[3,7, 76, 11, 22, 37, 56,2],[T, T, F, T, F, F, F, T]}
โData: [Age, Do you love Nutella?]
โข Partitioning will create
โ{[train data], [train labels],[test data], [test labels]}
โWe usually split the data on a ration of 9:1
โThere is a tradeoff between the effectiveness of
the test and the learning we could provide to the
classifier
โข We will look at a partitioning function later](https://image.slidesharecdn.com/introtomachinelearningwithscikit-learn-150623073429-lva1-app6891/85/Intro-to-machine-learning-with-scikit-learn-7-320.jpg)
![20
Iris Data
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn import datasets
iris = datasets.load_iris()
X = iris.data[:, :2] # we only take the first two features.
Y = iris.target
x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5](https://image.slidesharecdn.com/introtomachinelearningwithscikit-learn-150623073429-lva1-app6891/85/Intro-to-machine-learning-with-scikit-learn-20-320.jpg)
![21
Plot Iris Data
plt.figure(2, figsize=(8, 6))
plt.clf()
plt.scatter(X[:, 0], X[:, 1],
c=Y, cmap=plt.cm.Paired)
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
plt.xticks(())
plt.yticks(())](https://image.slidesharecdn.com/introtomachinelearningwithscikit-learn-150623073429-lva1-app6891/85/Intro-to-machine-learning-with-scikit-learn-21-320.jpg)
![22
Add PCA for better classification
fig = plt.figure(1, figsize=(8, 6))
ax = Axes3D(fig, elev=-150, azim=110)
X_reduced = PCA(n_components=3).fit_transform(iris.data)
ax.scatter(X_reduced[:, 0], X_reduced[:, 1], X_reduced[:, 2], c=Y,
cmap=plt.cm.Paired)
ax.set_title("First three PCA directions")
ax.set_xlabel("1st eigenvector")
ax.w_xaxis.set_ticklabels([])
ax.set_ylabel("2nd eigenvector")
ax.w_yaxis.set_ticklabels([])
ax.set_zlabel("3rd eigenvector")
ax.w_zaxis.set_ticklabels([])
plt.show()](https://image.slidesharecdn.com/introtomachinelearningwithscikit-learn-150623073429-lva1-app6891/85/Intro-to-machine-learning-with-scikit-learn-22-320.jpg)
Intro to machine learning with scikit learn
- 2. 2 INTRO TO ML PROGRAMMING
- 3. 3 ML Programming 1. Get Data Get labels for supervised learning 1. Create a classifier 2. Train the classifier 3. Predict test data 4. Evaluate predictor accuracy *Configure and improve by repeating 2-5
- 5. 5 Get Data & Labels โข Sources โOpen data sources โCollect on your own โข Verify data validity and correctness โข Wrangle data โmake it readable by computer โFilter it โข Remove Outliers PANDAS Python library could assist in pre- processing & data manipulation before ML http://pandas.pydata.org/
- 6. 6 Pre-Processing ๏งChange formatting ๏งRemove redundant data ๏งFilter Data (take partial data) ๏งRemove Outliers ๏งLabel ๏งSplit for testing (10/90, 20/80)
- 7. 7 Data Partitioning โข Data and labels โ{[data], [labels]} โ{[3,7, 76, 11, 22, 37, 56,2],[T, T, F, T, F, F, F, T]} โData: [Age, Do you love Nutella?] โข Partitioning will create โ{[train data], [train labels],[test data], [test labels]} โWe usually split the data on a ration of 9:1 โThere is a tradeoff between the effectiveness of the test and the learning we could provide to the classifier โข We will look at a partitioning function later
- 8. 8 Learn (The โSmart Partโ) ๏งClassification ๏งIf the output is discrete to a limited amount of classes (groups) ๏งRegression ๏งIf the output is continues
- 10. 10 Create Classifier ๏งFor most SUPERVISED LEARNING algorithms this would be ๏งC = ClassifyAlg(Params) ๏งIts up to us (ML guys) to set the best params ๏งHow? 1. We could develop a hunch for it 2. Perform an exhaustive search
- 11. 11 Train the classifier We assigned C = ClassifyAlg(Params) This is a general algorithm with some initalizer and configurations. In this stage we train it using: C.fit(Data, Labels)
- 12. 12 Predict ๏งAfter we have a trained Algorithm classifier C ๏งPrdeicted_Labels = C.predict(Data)
- 13. 13 Predictor Evaluation ๏งWe are not done yet ๏งThere is a need to evaluate the predictor accuracy in comparison to other predictors and to the system requirements ๏งWe will learn several methods for this
- 14. 14 ENVIRONMENT
- 15. 15 The Environment โข There are many existing environments and tools we could use โMatlab with Machine learning toolbox โApache Mahout โPython with Scikit-learn โข Additional tools โHadoop / Map-Reduce to accelerate and parallelize large data set processing โAmazon ML tools โNVIDIA Tools
- 16. 16 Scikit-learn โข Installation Instructions in http://scikit-learn.org/stable/install.html#install-official-release โข Depends on two other libraries โข numpy and scipy โข Easiest way to install on windows: โข Install WinPython http://sourceforge.net/projects/winpython/files/WinPython_2.7/2.7.9.4/ โLets install this together For Linux / Mac computers just install the 3 libs separately using PIP
- 17. 17 THE DATA
- 18. 18 Data sets ๏งThere are many data sets to work on ๏งOne of them is the Iris data classification into three groups. It has an interesting story you could google later ๏งWell work on the iris data
- 19. 19 Lab A โ Plot the Iris data ๏งPlot septal length vs septal width with labels ONLY ๏งHow? Google Iris data and the scikit learn environment ๏งTry to understand the second part of the program with the PCA
- 20. 20 Iris Data import matplotlib.pyplot as plt from mpl_toolkits.mplot3d import Axes3D from sklearn import datasets iris = datasets.load_iris() X = iris.data[:, :2] # we only take the first two features. Y = iris.target x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5 y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
- 21. 21 Plot Iris Data plt.figure(2, figsize=(8, 6)) plt.clf() plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired) plt.xlabel('Sepal length') plt.ylabel('Sepal width') plt.xlim(x_min, x_max) plt.ylim(y_min, y_max) plt.xticks(()) plt.yticks(())
- 22. 22 Add PCA for better classification fig = plt.figure(1, figsize=(8, 6)) ax = Axes3D(fig, elev=-150, azim=110) X_reduced = PCA(n_components=3).fit_transform(iris.data) ax.scatter(X_reduced[:, 0], X_reduced[:, 1], X_reduced[:, 2], c=Y, cmap=plt.cm.Paired) ax.set_title("First three PCA directions") ax.set_xlabel("1st eigenvector") ax.w_xaxis.set_ticklabels([]) ax.set_ylabel("2nd eigenvector") ax.w_yaxis.set_ticklabels([]) ax.set_zlabel("3rd eigenvector") ax.w_zaxis.set_ticklabels([]) plt.show()
- 24. 24
- 25. 25 Thank you! More About me: Yossi CohenYossi Cohen [email protected]@gmail.com +972-545-313092+972-545-313092 ๏ง Video compression and computer vision enthusiast & lecturer ๏ง Surfer