file header<\/h3>\n<\/li>\n<\/ul>\n
[code language=”python”]
\nfrom sklearn.decomposition import PCA
\nfrom sklearn.lda import LDA
\nfrom numpy import genfromtxt
\nfrom sklearn import preprocessing
\nimport numpy as np
\n[\/code]<\/p>\n
- \n
- \n
load data from csv file<\/h3>\n<\/li>\n<\/ul>\n
[code language=”python”]
\nraw_sensor = genfromtxt(‘sensor.csv’, dtype=’string’, delimiter=’,’)
\nstring_sensor = raw_sensor[1:,1:9]
\nsensor = string_sensor.astype(np.float)
\nX = sensor[:100, 6:8]#0:2 acceleration data, 3:5 gyroscope data, 6:8 Magnetic data
\n[\/code]
\n<\/p>\n- \n
- \n
convert label to integer<\/h3>\n<\/li>\n<\/ul>\n
[code language=”python”]
\n#convert label to integer
\nraw_label = raw_sensor[1:,16]
\nle = preprocessing.LabelEncoder()
\nle.fit([&amp;quot;Sit&amp;quot;, &amp;quot;Lie&amp;quot;, &amp;quot;Stand&amp;quot;, &amp;quot;Walk&amp;quot;])
\ntarget = le.transform(raw_label)
\ntarget_names = np.array([&amp;quot;Sit&amp;quot;, &amp;quot;Lie&amp;quot;, &amp;quot;Stand&amp;quot;, &amp;quot;Walk&amp;quot;])
\ny = target
\n[\/code]<\/p>\n- \n
- \n
plot two or one dimension data as scatter diagram<\/h3>\n<\/li>\n<\/ul>\n
[code language=”python”]
\nplt.figure()
\nfor c, i, target_name in zip(&amp;quot;rgby&amp;quot;, [0, 1, 2, 3], target_names):
\n #plt.scatter(X_r[y == i, 0], X_r[y == i, 1], c=c, label=target_name)#for 2 dimensions data
\n plt.plot(X_r, np.zeros_like(X_r) + 0, ‘x’, c=c, label = target_name)#for 1 dimension data
\nplt.legend()
\nplt.title(‘PCA of Magnetic dataset’)
\n[\/code]<\/p>\n- \n
- \n
plot two dimension data as scatter diagram (style 2)<\/h3>\n<\/li>\n<\/ul>\n
[code language=”python”]
\nplt.figure(2, figsize=(8, 6))
\nplt.clf()<\/p>\n# Plot the training points
\nplt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired)
\nplt.xlabel(‘Sepal length’)
\nplt.ylabel(‘Sepal width’)<\/p>\nplt.xlim(x_min, x_max)
\nplt.ylim(y_min, y_max)
\nplt.xticks(())
\nplt.yticks(())
\n[\/code]<\/p>\n![\"\u5fae\u4fe1\u622a\u56fe_20160229100924\"](\"https:\/\/posuer000.files.wordpress.com\/2016\/02\/e5beaee4bfa1e688aae59bbe_20160229100924.png\")
<\/p>\n- \n
- \n
plot 3D scatter diagram<\/h3>\n<\/li>\n<\/ul>\n
[code language=”python”]
\n# To getter a better understanding of interaction of the dimensions
\n# plot the first three PCA dimensions
\nfig = plt.figure(1, figsize=(8, 6))
\nax = Axes3D(fig, elev=-150, azim=110)
\nX_reduced = PCA(n_components=3).fit_transform(iris.data)
\nax.scatter(X_reduced[:, 0], X_reduced[:, 1], X_reduced[:, 2], c=Y,
\n cmap=plt.cm.Paired)
\nax.set_title(&amp;quot;First three PCA directions&amp;quot;)
\nax.set_xlabel(&amp;quot;1st eigenvector&amp;quot;)
\nax.w_xaxis.set_ticklabels([])
\nax.set_ylabel(&amp;quot;2nd eigenvector&amp;quot;)
\nax.w_yaxis.set_ticklabels([])
\nax.set_zlabel(&amp;quot;3rd eigenvector&amp;quot;)
\nax.w_zaxis.set_ticklabels([])
\n[\/code]
\n![\"\u5fae\u4fe1\u622a\u56fe_20160229101736\"](\"https:\/\/posuer000.files.wordpress.com\/2016\/02\/e5beaee4bfa1e688aae59bbe_20160229101736.png\")
<\/p>\n- \n
- \n
Stack arrays in sequence vertically (row wise).<\/h3>\n<\/li>\n<\/ul>\n
[code language=”python”]
\nS = np.vstack((sensor[:,1],sensor[:,2])).T #.T matrix transpose
\n[\/code]<\/p>\n\nStack arrays in sequence vertically (row wise).
\nTake a sequence of arrays and stack them vertically to make a single array. Rebuild arrays divided by vsplit.\n<\/p>\nexample<\/h5>\n
[code language=”python”]
\n&gt;&gt;&gt; a = np.array([1, 2, 3])
\n&gt;&gt;&gt; b = np.array([2, 3, 4])
\n&gt;&gt;&gt; np.vstack((a,b))
\narray([[1, 2, 3],
\n [2, 3, 4]])
\n[\/code]<\/p>\n","protected":false},"excerpt":{"rendered":"source from python.org file header [code language=”python”] from sklearn.decomposition import PCA from sklearn.lda import LDA from numpy import genfromtxt from sklearn import preprocessing import numpy as np [\/code] load data from csv file [code language=”python”] raw_sensor = genfromtxt(‘sensor.csv’, dtype=’string’, delimiter=’,’) string_sensor = raw_sensor[1:,1:9] sensor = string_sensor.astype(np.float) X = sensor[:100, 6:8]#0:2…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[],"class_list":["post-56","post","type-post","status-publish","format-standard","hentry","category-techniques"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/wanggengyu.com\/index.php?rest_route=\/wp\/v2\/posts\/56","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wanggengyu.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wanggengyu.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wanggengyu.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/wanggengyu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=56"}],"version-history":[{"count":0,"href":"https:\/\/wanggengyu.com\/index.php?rest_route=\/wp\/v2\/posts\/56\/revisions"}],"wp:attachment":[{"href":"https:\/\/wanggengyu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=56"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wanggengyu.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=56"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wanggengyu.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=56"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
- \n
- \n
- \n
- \n
- \n