Register
Login
Resources
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Product
Data Engine LLMs Platform Enterprise
Pricing Explore
Connect to our Discord channel
Resources  
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Explore Pricing
Product  
Data Engine LLMs Platform Enterprise
Connect to Dagshub Discord channel
Register
Login

csinva
/
auxilin-prediction
mirror of https://github.com/Yu-Group/auxilin-prediction

Watch 1
Issues   Discussions 0

rf_neighbors.html 12 KB
Permalink History Raw

You have to be logged in to leave a comment. Sign In
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227 
  1. <!doctype html>
    2. 

  2. <html lang="en">
    3. 

  3. <head>
    4. 

  4. <meta charset="utf-8">
    5. 

  5. <meta name="viewport" content="width=device-width, initial-scale=1, minimum-scale=1" />
    6. 

  6. <meta name="generator" content="pdoc 0.7.2" />
    7. 

  7. <title>src.ref.rf_neighbors API documentation</title>
    8. 

  8. <meta name="description" content="" />
    9. 

  9. <link href='https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.0/normalize.min.css' rel='stylesheet'>
    10. 

  10. <link href='https://cdnjs.cloudflare.com/ajax/libs/10up-sanitize.css/8.0.0/sanitize.min.css' rel='stylesheet'>
    11. 

  11. <link href="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/styles/github.min.css" rel="stylesheet">
    12. 

  12. <style>.flex{display:flex !important}body{line-height:1.5em}#content{padding:20px}#sidebar{padding:30px;overflow:hidden}.http-server-breadcrumbs{font-size:130%;margin:0 0 15px 0}#footer{font-size:.75em;padding:5px 30px;border-top:1px solid #ddd;text-align:right}#footer p{margin:0 0 0 1em;display:inline-block}#footer p:last-child{margin-right:30px}h1,h2,h3,h4,h5{font-weight:300}h1{font-size:2.5em;line-height:1.1em}h2{font-size:1.75em;margin:1em 0 .50em 0}h3{font-size:1.4em;margin:25px 0 10px 0}h4{margin:0;font-size:105%}a{color:#058;text-decoration:none;transition:color .3s ease-in-out}a:hover{color:#e82}.title code{font-weight:bold}h2[id^="header-"]{margin-top:2em}.ident{color:#900}pre code{background:#f8f8f8;font-size:.8em;line-height:1.4em}code{background:#f2f2f1;padding:1px 4px;overflow-wrap:break-word}h1 code{background:transparent}pre{background:#f8f8f8;border:0;border-top:1px solid #ccc;border-bottom:1px solid #ccc;margin:1em 0;padding:1ex}#http-server-module-list{display:flex;flex-flow:column}#http-server-module-list div{display:flex}#http-server-module-list dt{min-width:10%}#http-server-module-list p{margin-top:0}.toc ul,#index{list-style-type:none;margin:0;padding:0}#index code{background:transparent}#index h3{border-bottom:1px solid #ddd}#index ul{padding:0}#index h4{font-weight:bold}#index h4 + ul{margin-bottom:.6em}@media (min-width:200ex){#index .two-column{column-count:2}}@media (min-width:300ex){#index .two-column{column-count:3}}dl{margin-bottom:2em}dl dl:last-child{margin-bottom:4em}dd{margin:0 0 1em 3em}#header-classes + dl > dd{margin-bottom:3em}dd dd{margin-left:2em}dd p{margin:10px 0}.name{background:#eee;font-weight:bold;font-size:.85em;padding:5px 10px;display:inline-block;min-width:40%}.name:hover{background:#e0e0e0}.name > span:first-child{white-space:nowrap}.name.class > span:nth-child(2){margin-left:.4em}.inherited{color:#999;border-left:5px solid #eee;padding-left:1em}.inheritance em{font-style:normal;font-weight:bold}.desc h2{font-weight:400;font-size:1.25em}.desc h3{font-size:1em}.desc dt code{background:inherit}.source summary,.git-link-div{color:#666;text-align:right;font-weight:400;font-size:.8em;text-transform:uppercase}.source summary > *{white-space:nowrap;cursor:pointer}.git-link{color:inherit;margin-left:1em}.source pre{max-height:500px;overflow:auto;margin:0}.source pre code{font-size:12px;overflow:visible}.hlist{list-style:none}.hlist li{display:inline}.hlist li:after{content:',\2002'}.hlist li:last-child:after{content:none}.hlist .hlist{display:inline;padding-left:1em}img{max-width:100%}.admonition{padding:.1em .5em;margin-bottom:1em}.admonition-title{font-weight:bold}.admonition.note,.admonition.info,.admonition.important{background:#aef}.admonition.todo,.admonition.versionadded,.admonition.tip,.admonition.hint{background:#dfd}.admonition.warning,.admonition.versionchanged,.admonition.deprecated{background:#fd4}.admonition.error,.admonition.danger,.admonition.caution{background:lightpink}</style>
    13. 

  13. <style media="screen and (min-width: 700px)">@media screen and (min-width:700px){#sidebar{width:30%}#content{width:70%;max-width:100ch;padding:3em 4em;border-left:1px solid #ddd}pre code{font-size:1em}.item .name{font-size:1em}main{display:flex;flex-direction:row-reverse;justify-content:flex-end}.toc ul ul,#index ul{padding-left:1.5em}.toc > ul > li{margin-top:.5em}}</style>
    14. 

  14. <style media="print">@media print{#sidebar h1{page-break-before:always}.source{display:none}}@media print{*{background:transparent !important;color:#000 !important;box-shadow:none !important;text-shadow:none !important}a[href]:after{content:" (" attr(href) ")";font-size:90%}a[href][title]:after{content:none}abbr[title]:after{content:" (" attr(title) ")"}.ir a:after,a[href^="javascript:"]:after,a[href^="#"]:after{content:""}pre,blockquote{border:1px solid #999;page-break-inside:avoid}thead{display:table-header-group}tr,img{page-break-inside:avoid}img{max-width:100% !important}@page{margin:0.5cm}p,h2,h3{orphans:3;widows:3}h1,h2,h3,h4,h5,h6{page-break-after:avoid}}</style>
    15. 

  15. </head>
    16. 

  16. <body>
    17. 

  17. <main>
    18. 

  18. <article id="content">
    19. 

  19. <header>
    20. 

  20. <h1 class="title">Module <code>src.ref.rf_neighbors</code></h1>
    21. 

  21. </header>
    22. 

  22. <section id="section-intro">
    23. 

  23. <details class="source">
    24. 

  24. <summary>
    25. 

  25. <span>Expand source code</span>
    26. 

  26. </summary>
    27. 

  27. <pre><code class="python">import sys
    28. 

  28. 

  29. import numpy as np
    30. 

  30. from sklearn.ensemble import RandomForestClassifier
    31. 

  31. from sklearn.feature_selection import SelectFromModel
    32. 

  32. from sklearn.linear_model import Lasso
    33. 

  33. from sklearn.model_selection import KFold
    34. 

  34. 

  35. sys.path.append(&#39;lib&#39;)
    36. 

  36. import collections
    37. 

  37. 

  38. cell_nums_feature_selection = np.array([1])
    39. 

  39. cell_nums_train = np.array([1, 2, 3, 4, 5])
    40. 

  40. cell_nums_test = np.array([6])
    41. 

  41. 

  42. 

  43. def get_rf_neighbors(df, feat_names, outcome_def=&#39;y_thresh&#39;,
    44. 

  44.                      balancing=&#39;ros&#39;, balancing_ratio=1, out_name=&#39;results/classify/test.pkl&#39;,
    45. 

  45.                      feature_selection=None, feature_selection_num=3, seed=42):
    46. 

  46.     # pre-processing same as train.train
    47. 

  47. 

  48.     np.random.seed(seed)
    49. 

  49.     X = df[feat_names]
    50. 

  50.     y = df[outcome_def].values
    51. 

  51. 

  52.     m = RandomForestClassifier(n_estimators=100)
    53. 

  53. 

  54.     kf = KFold(n_splits=len(cell_nums_train))
    55. 

  55. 

  56.     # feature selection on cell num 1    
    57. 

  57.     feature_selector = None
    58. 

  58.     if feature_selection is not None:
    59. 

  59.         if feature_selection == &#39;select_lasso&#39;:
    60. 

  60.             feature_selector_model = Lasso()
    61. 

  61.         elif feature_selection == &#39;select_rf&#39;:
    62. 

  62.             feature_selector_model = RandomForestClassifier()
    63. 

  63.         # select only feature_selection_num features
    64. 

  64.         feature_selector = SelectFromModel(feature_selector_model, threshold=-np.inf,
    65. 

  65.                                            max_features=feature_selection_num)
    66. 

  66.         idxs = df.cell_num.isin(cell_nums_feature_selection)
    67. 

  67.         feature_selector.fit(X[idxs], y[idxs])
    68. 

  68.         X = feature_selector.transform(X)
    69. 

  69.         support = np.array(feature_selector.get_support())
    70. 

  70.     else:
    71. 

  71.         support = np.ones(len(feat_names)).astype(np.bool)
    72. 

  72. 

  73.     # split testing data based on cell num
    74. 

  74.     idxs_test = df.cell_num.isin(cell_nums_test)
    75. 

  75.     X_test, Y_test = X[idxs_test], y[idxs_test]
    76. 

  76.     idxs_train = df.cell_num.isin(cell_nums_train)
    77. 

  77.     X_train, Y_train = X[idxs_train], y[idxs_train]
    78. 

  78.     # num_pts_by_fold_cv = []
    79. 

  79. 

  80.     # build dictionary, key is leaf node, value is list of training samples in the node
    81. 

  81. 

  82.     m.fit(X_train, Y_train)
    83. 

  83.     node_indices = m.apply(X_train)
    84. 

  84.     node_indices_test = m.apply(X_test)
    85. 

  85.     similarity_matrix = np.zeros((len(X_test), len(X_train)))
    86. 

  86.     for tree in range(100):
    87. 

  87.         node_samples = collections.defaultdict(list)
    88. 

  88.         for i in range(len(X_train)):
    89. 

  89.             node_samples[node_indices[i, tree]].append(i)
    90. 

  90.         for i in range(len(X_test)):
    91. 

  91.             node = node_indices_test[i, tree]
    92. 

  92.             for j in node_samples[node]:
    93. 

  93.                 similarity_matrix[i, j] += 1
    94. 

  94.     preds_proba = m.predict_proba(X_test)[:, 1]
    95. 

  95. 

  96.     # nearest neighbors and similarity
    97. 

  97.     nearest_neighbors = [np.argsort(similarity_matrix[i, :])[::-1][:10] for i in range(len(X_test))]
    98. 

  98.     similarity = [np.sort(similarity_matrix[i, :])[::-1][:10] for i in range(len(X_test))]
    99. 

  99. 

  100.     idxs_test = np.where(idxs_test == True)
    101. 

  101.     idxs_train = np.where(idxs_train == True)
    102. 

  102.     df_train = df.iloc[idxs_train]
    103. 

  103.     df_test = df.iloc[idxs_test]
    104. 

  104. 

  105.     df_test[&#39;preds_proba&#39;] = preds_proba
    106. 

  106.     df_test[&#39;nearest_neighbors&#39;] = nearest_neighbors
    107. 

  107.     df_test[&#39;similarity&#39;] = similarity
    108. 

  108. 

  109.     return df_train, df_test</code></pre>
    110. 

  110. </details>
    111. 

  111. </section>
    112. 

  112. <section>
    113. 

  113. </section>
    114. 

  114. <section>
    115. 

  115. </section>
    116. 

  116. <section>
    117. 

  117. <h2 class="section-title" id="header-functions">Functions</h2>
    118. 

  118. <dl>
    119. 

  119. <dt id="src.ref.rf_neighbors.get_rf_neighbors"><code class="name flex">
    120. 

  120. <span>def <span class="ident">get_rf_neighbors</span></span>(<span>df, feat_names, outcome_def='y_thresh', balancing='ros', balancing_ratio=1, out_name='results/classify/test.pkl', feature_selection=None, feature_selection_num=3, seed=42)</span>
    121. 

  121. </code></dt>
    122. 

  122. <dd>
    123. 

  123. <section class="desc"></section>
    124. 

  124. <details class="source">
    125. 

  125. <summary>
    126. 

  126. <span>Expand source code</span>
    127. 

  127. </summary>
    128. 

  128. <pre><code class="python">def get_rf_neighbors(df, feat_names, outcome_def=&#39;y_thresh&#39;,
    129. 

  129.                      balancing=&#39;ros&#39;, balancing_ratio=1, out_name=&#39;results/classify/test.pkl&#39;,
    130. 

  130.                      feature_selection=None, feature_selection_num=3, seed=42):
    131. 

  131.     # pre-processing same as train.train
    132. 

  132. 

  133.     np.random.seed(seed)
    134. 

  134.     X = df[feat_names]
    135. 

  135.     y = df[outcome_def].values
    136. 

  136. 

  137.     m = RandomForestClassifier(n_estimators=100)
    138. 

  138. 

  139.     kf = KFold(n_splits=len(cell_nums_train))
    140. 

  140. 

  141.     # feature selection on cell num 1    
    142. 

  142.     feature_selector = None
    143. 

  143.     if feature_selection is not None:
    144. 

  144.         if feature_selection == &#39;select_lasso&#39;:
    145. 

  145.             feature_selector_model = Lasso()
    146. 

  146.         elif feature_selection == &#39;select_rf&#39;:
    147. 

  147.             feature_selector_model = RandomForestClassifier()
    148. 

  148.         # select only feature_selection_num features
    149. 

  149.         feature_selector = SelectFromModel(feature_selector_model, threshold=-np.inf,
    150. 

  150.                                            max_features=feature_selection_num)
    151. 

  151.         idxs = df.cell_num.isin(cell_nums_feature_selection)
    152. 

  152.         feature_selector.fit(X[idxs], y[idxs])
    153. 

  153.         X = feature_selector.transform(X)
    154. 

  154.         support = np.array(feature_selector.get_support())
    155. 

  155.     else:
    156. 

  156.         support = np.ones(len(feat_names)).astype(np.bool)
    157. 

  157. 

  158.     # split testing data based on cell num
    159. 

  159.     idxs_test = df.cell_num.isin(cell_nums_test)
    160. 

  160.     X_test, Y_test = X[idxs_test], y[idxs_test]
    161. 

  161.     idxs_train = df.cell_num.isin(cell_nums_train)
    162. 

  162.     X_train, Y_train = X[idxs_train], y[idxs_train]
    163. 

  163.     # num_pts_by_fold_cv = []
    164. 

  164. 

  165.     # build dictionary, key is leaf node, value is list of training samples in the node
    166. 

  166. 

  167.     m.fit(X_train, Y_train)
    168. 

  168.     node_indices = m.apply(X_train)
    169. 

  169.     node_indices_test = m.apply(X_test)
    170. 

  170.     similarity_matrix = np.zeros((len(X_test), len(X_train)))
    171. 

  171.     for tree in range(100):
    172. 

  172.         node_samples = collections.defaultdict(list)
    173. 

  173.         for i in range(len(X_train)):
    174. 

  174.             node_samples[node_indices[i, tree]].append(i)
    175. 

  175.         for i in range(len(X_test)):
    176. 

  176.             node = node_indices_test[i, tree]
    177. 

  177.             for j in node_samples[node]:
    178. 

  178.                 similarity_matrix[i, j] += 1
    179. 

  179.     preds_proba = m.predict_proba(X_test)[:, 1]
    180. 

  180. 

  181.     # nearest neighbors and similarity
    182. 

  182.     nearest_neighbors = [np.argsort(similarity_matrix[i, :])[::-1][:10] for i in range(len(X_test))]
    183. 

  183.     similarity = [np.sort(similarity_matrix[i, :])[::-1][:10] for i in range(len(X_test))]
    184. 

  184. 

  185.     idxs_test = np.where(idxs_test == True)
    186. 

  186.     idxs_train = np.where(idxs_train == True)
    187. 

  187.     df_train = df.iloc[idxs_train]
    188. 

  188.     df_test = df.iloc[idxs_test]
    189. 

  189. 

  190.     df_test[&#39;preds_proba&#39;] = preds_proba
    191. 

  191.     df_test[&#39;nearest_neighbors&#39;] = nearest_neighbors
    192. 

  192.     df_test[&#39;similarity&#39;] = similarity
    193. 

  193. 

  194.     return df_train, df_test</code></pre>
    195. 

  195. </details>
    196. 

  196. </dd>
    197. 

  197. </dl>
    198. 

  198. </section>
    199. 

  199. <section>
    200. 

  200. </section>
    201. 

  201. </article>
    202. 

  202. <nav id="sidebar">
    203. 

  203. <h1>Index</h1>
    204. 

  204. <div class="toc">
    205. 

  205. <ul></ul>
    206. 

  206. </div>
    207. 

  207. <ul id="index">
    208. 

  208. <li><h3>Super-module</h3>
    209. 

  209. <ul>
    210. 

  210. <li><code><a title="src.ref" href="index.html">src.ref</a></code></li>
    211. 

  211. </ul>
    212. 

  212. </li>
    213. 

  213. <li><h3><a href="#header-functions">Functions</a></h3>
    214. 

  214. <ul class="">
    215. 

  215. <li><code><a title="src.ref.rf_neighbors.get_rf_neighbors" href="#src.ref.rf_neighbors.get_rf_neighbors">get_rf_neighbors</a></code></li>
    216. 

  216. </ul>
    217. 

  217. </li>
    218. 

  218. </ul>
    219. 

  219. </nav>
    220. 

  220. </main>
    221. 

  221. <footer id="footer">
    222. 

  222. <p>Generated by <a href="https://pdoc3.github.io/pdoc"><cite>pdoc</cite> 0.7.2</a>.</p>
    223. 

  223. </footer>
    224. 

  224. <script src="https://cdnjs.cloudflare.com/ajax/libs/highlight.js/9.12.0/highlight.min.js"></script>
    225. 

  225. <script>hljs.initHighlightingOnLoad()</script>
    226. 

  226. </body>
    227. 

  227. </html>
    228.
Prev
Next
Tip!

Press p or to see the previous file or, n or to see the next file

Comments

Write Preview
Loading...
Integrate Google Cloud Storage
Use Google Storage
Select bucket
Upload key
Finish

Use Google Cloud Storage!

Browsing data directories saved to Google Cloud Storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your Google Storage bucket

Service Account Key

Congratulations!

auxilin-prediction is now integrated with Google Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate AWS S3
Use S3 remote
Select bucket
Access key
Finish

Use AWS S3 as storage!

Browsing data directories saved to S3 is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your S3 bucket

Access key (If needed)

Congratulations!

auxilin-prediction is now integrated with AWS S3!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate S3 compatible storage
Use S3 like remote
Select bucket
Access key
Finish

Use any S3 compatible storage!

Browsing data directories saved to S3 compatible storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your S3 bucket

Access key (If needed)

Congratulations!

auxilin-prediction is now integrated with your S3 compatible storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes
Integrate Azure Cloud Storage
Use Azure Storage
Select bucket
Set key
Finish

Use Azure Cloud Storage!

Browsing data directories saved to Azure Cloud Storage is possible with DAGsHub. Let's configure your repository to easily display your data in the context of any commit!

Specify your Azure Storage bucket

Access key (If needed)

Congratulations!

auxilin-prediction is now integrated with Azure Cloud Storage!

Delete Storage Key

Are you sure you want to delete this access key?

No
Yes