#
#??tsne.py
#
#?Implementation?of?t-SNE?in?Python.?The?implementation?was?tested?on?Python
#?2.7.10?and?it?requires?a?working?installation?of?NumPy.?The?implementation
#?comes?with?an?example?on?the?MNIST?dataset.?In?order?to?plot?the
#?results?of?this?example?a?working?installation?of?matplotlib?is?required.
#
#?The?example?can?be?run?by?executing:?‘ipython?tsne.py‘
#
#
#??Created?by?Laurens?van?der?Maaten?on?20-12-08.
#??Copyright?（c）?2008?Tilburg?University.?All?rights?reserved.

import?numpy?as?np
import?pylab


def?Hbeta（D=np.array（[]）?beta=1.0）:
????“““
????????Compute?the?perplexity?and?the?P-row?for?a?specific?value?of?the
????????precision?of?a?Gaussian?distribution.
????“““

????#?Compute?P-row?and?corresponding?perplexity
????P?=?np.exp（-D.copy（）?*?beta）
????sumP?=?sum（P）
????H?=?np.log（sumP）?+?beta?*?np.sum（D?*?P）?/?sumP
????P?=?P?/?sumP
????return?H?P


def?x2p（X=np.array（[]）?tol=1e-5?perplexity=30.0）:
????“““
????????Performs?a?binary?search?to?get?P-values?in?such?a?way?that?each
????????conditional?Gaussian?has?the?same?perplexity.
????“““

????#?Initialize?some?variables
????print（“Computing?pairwise?distances...“）
????（n?d）?=?X.shape
????sum_X?=?np.sum（np.square（X）?1）
????D?=?np.add（np.add（-2?*?np.dot（X?X.T）?sum_X）.T?sum_X）
????P?=?np.zeros（（n?n））
????beta?=?np.ones（（n?1））
????logU?=?np.log（perplexity）

????#?Loop?over?all?datapoints
????for?i?in?range（n）:

????????#?Print?progress
????????if?i?%?500?==?0:
????????????print（“Computing?P-values?for?point?%d?of?%d...“?%?（i?n））

????????#?Compute?the?Gaussian?kernel?and?entropy?for?the?current?precision
????????betamin?=?-np.inf
????????betamax?=?np.inf
????????Di?=?D[i?np.concatenate（（np.r_[0:i]?np.r_[i+1:n]））]
????????（H?thisP）?=?Hbeta（Di?beta[i]）

????????#?Evaluate?whether?the?perplexity?is?within?tolerance
????????Hdiff?=?H?-?logU
????????tries?=?0
????????while?np.abs（Hdiff）?>?tol?and?tries?
????????????#?If?not?increase?or?decrease?precision
????????????if?Hdiff?>?0:
????????????????betamin?=?beta[i].copy（）
????????????????if?betamax?==?np.inf?or?betamax?==?-np.inf:
????????????????????beta[i]?=?beta[i]?*?2.
????????????????else:
????????????????????beta[i]?=?（beta[i]?+?betamax）?/?2.
????????????else:
????????????????betamax?=?beta[i].copy（）
????????????????if?betamin?==?np.inf?or?betamin?==?-np.inf:
????????????????????beta[i]?=?beta[i]?/?2.
????????????????else:
????????????????????beta[i]?=?（beta[i]?+?betamin）?/?2.

????????????#?Recompute?the?values
????????????（H?thisP）?=?Hbeta（Di?beta[i]）
????????????Hdiff?=?H?-?logU
????????????tries?+=?1

????????#?Set?the?final?row?of?P
????????P[i?np.concatenate（（np.r_[0:i]?np.r_[i+1:n]））]?=?thisP

????#?Return?final?P-matrix
????print（“Mean?value?of?sigma:?%f“?%?np.mean（np.sqrt（1?/?beta）））
????return?P


def?pca（X=np.array（[]）?no_dims=50）:
????“““
????????Runs?PCA?on?the?NxD?array?X?in?order?to?reduce?its?dimensionality?to
????????no_dims?dimensions.
????“““

????print（“Preprocessing?the?data?using?P

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????目錄???????????0??2019-01-09?17:13??tsne_python\
?????文件???????42500??2008-12-30?18:13??tsne_python\mnist2500_labels.txt
?????目錄???????????0??2019-03-18?14:46??__MACOSX\
?????目錄???????????0??2019-03-18?14:46??__MACOSX\tsne_python\
?????文件?????????268??2008-12-30?18:13??__MACOSX\tsne_python\._mnist2500_labels.txt
?????文件????31362500??2008-12-30?18:13??tsne_python\mnist2500_X.txt
?????文件?????????268??2008-12-30?18:13??__MACOSX\tsne_python\._mnist2500_X.txt
?????文件????????5807??2017-12-15?22:27??tsne_python\tsne.py
?????文件?????????549??2017-12-15?22:27??__MACOSX\tsne_python\._tsne.py
?????文件?????????212??2019-01-09?17:13??__MACOSX\._tsne_python