Skip to content

Commit b2f298b

Browse files
LinXueyuanStdioLinXueyuanStdio
committed
mv all data to ./data
1 parent 2d73818 commit b2f298b

File tree

3 files changed

+162
-262
lines changed

3 files changed

+162
-262
lines changed

‎《Python数据挖掘入门与实践》/0.数据挖掘流程简单示例10min.ipynb

Lines changed: 95 additions & 95 deletions
Original file line numberDiff line numberDiff line change
@@ -51,11 +51,11 @@
5151
"output_type": "stream",
5252
"text": [
5353
"(100, 5)\n",
54-
"[[ 0. 0. 0. 1. 1.]\n",
55-
" [ 0. 1. 0. 1. 1.]\n",
54+
"[[ 0. 1. 1. 0. 1.]\n",
5655
" [ 0. 1. 0. 0. 0.]\n",
57-
" [ 0. 1. 0. 0. 0.]\n",
58-
" [ 0. 0. 0. 1. 1.]]\n"
56+
" [ 0. 0. 1. 1. 1.]\n",
57+
" [ 0. 0. 1. 1. 1.]\n",
58+
" [ 0. 1. 0. 1. 0.]]\n"
5959
]
6060
}
6161
],
@@ -106,11 +106,11 @@
106106
" X[i][4] = 1\n",
107107
" if X[i].sum() == 0:\n",
108108
" X[i][4] = 1 # Must buy something, so gets bananas\n",
109-
"np.savetxt(\"affinity_dataset.txt\", X, fmt='%d') # 保存\n",
109+
"np.savetxt(\"./data/affinity_dataset.txt\", X, fmt='%d') # 保存\n",
110110
"\n",
111111
"\n",
112112
"# 读取数据\n",
113-
"dataset_filename = \"affinity_dataset.txt\"\n",
113+
"dataset_filename = \"./data/affinity_dataset.txt\"\n",
114114
"X = np.loadtxt(dataset_filename) # 加载数据\n",
115115
"n_samples, n_features = X.shape\n",
116116
"print(X.shape)\n",
@@ -128,11 +128,11 @@
128128
"name": "stdout",
129129
"output_type": "stream",
130130
"text": [
131-
"买苹果的有33人\n",
132-
"买了苹果又买香蕉的有20人\n",
133-
"买了苹果不买香蕉的有13人\n",
134-
"支持度support = 20 置信度confidence = 0.606.\n",
135-
"置信度confidence的百分比形式为 60.6%.\n"
131+
"买苹果的有39人\n",
132+
"买了苹果又买香蕉的有24人\n",
133+
"买了苹果不买香蕉的有15人\n",
134+
"支持度support = 24 置信度confidence = 0.615.\n",
135+
"置信度confidence的百分比形式为 61.5%.\n"
136136
]
137137
}
138138
],
@@ -209,85 +209,85 @@
209209
"name": "stdout",
210210
"output_type": "stream",
211211
"text": [
212-
"Rule: 买了bread，又买milk\n",
213-
" - 置信度Confidence: 0.519\n",
214-
" - 支持度Support: 14\n",
215-
"\n",
216212
"Rule: 买了milk，又买cheese\n",
217-
" - 置信度Confidence: 0.204\n",
218-
" - 支持度Support: 10\n",
213+
" - 置信度Confidence: 0.174\n",
214+
" - 支持度Support: 8\n",
215+
"\n",
216+
"Rule: 买了bread，又买milk\n",
217+
" - 置信度Confidence: 0.535\n",
218+
" - 支持度Support: 23\n",
219219
"\n",
220220
"Rule: 买了apples，又买cheese\n",
221-
" - 置信度Confidence: 0.545\n",
222-
" - 支持度Support: 18\n",
221+
" - 置信度Confidence: 0.487\n",
222+
" - 支持度Support: 19\n",
223223
"\n",
224224
"Rule: 买了milk，又买apples\n",
225-
" - 置信度Confidence: 0.184\n",
226-
" - 支持度Support: 9\n",
225+
" - 置信度Confidence: 0.326\n",
226+
" - 支持度Support: 15\n",
227+
"\n",
228+
"Rule: 买了bread，又买apples\n",
229+
" - 置信度Confidence: 0.256\n",
230+
" - 支持度Support: 11\n",
227231
"\n",
228232
"Rule: 买了apples，又买bread\n",
229-
" - 置信度Confidence: 0.182\n",
230-
" - 支持度Support: 6\n",
233+
" - 置信度Confidence: 0.282\n",
234+
" - 支持度Support: 11\n",
231235
"\n",
232-
"Rule: 买了bananas，又买milk\n",
233-
" - 置信度Confidence: 0.410\n",
234-
" - 支持度Support: 25\n",
236+
"Rule: 买了apples，又买bananas\n",
237+
" - 置信度Confidence: 0.615\n",
238+
" - 支持度Support: 24\n",
235239
"\n",
236240
"Rule: 买了apples，又买milk\n",
237-
" - 置信度Confidence: 0.273\n",
238-
" - 支持度Support: 9\n",
241+
" - 置信度Confidence: 0.385\n",
242+
" - 支持度Support: 15\n",
239243
"\n",
240244
"Rule: 买了milk，又买bananas\n",
241-
" - 置信度Confidence: 0.510\n",
242-
" - 支持度Support: 25\n",
245+
" - 置信度Confidence: 0.435\n",
246+
" - 支持度Support: 20\n",
243247
"\n",
244248
"Rule: 买了cheese，又买bananas\n",
245-
" - 置信度Confidence: 0.564\n",
246-
" - 支持度Support: 22\n",
249+
" - 置信度Confidence: 0.806\n",
250+
" - 支持度Support: 29\n",
247251
"\n",
248252
"Rule: 买了cheese，又买bread\n",
249-
" - 置信度Confidence: 0.205\n",
250-
" - 支持度Support: 8\n",
253+
" - 置信度Confidence: 0.111\n",
254+
" - 支持度Support: 4\n",
251255
"\n",
252256
"Rule: 买了cheese，又买apples\n",
253-
" - 置信度Confidence: 0.462\n",
254-
" - 支持度Support: 18\n",
257+
" - 置信度Confidence: 0.528\n",
258+
" - 支持度Support: 19\n",
255259
"\n",
256260
"Rule: 买了cheese，又买milk\n",
257-
" - 置信度Confidence: 0.256\n",
258-
" - 支持度Support: 10\n",
261+
" - 置信度Confidence: 0.222\n",
262+
" - 支持度Support: 8\n",
259263
"\n",
260264
"Rule: 买了bananas，又买apples\n",
261-
" - 置信度Confidence: 0.328\n",
262-
" - 支持度Support: 20\n",
265+
" - 置信度Confidence: 0.393\n",
266+
" - 支持度Support: 24\n",
263267
"\n",
264268
"Rule: 买了bread，又买bananas\n",
265-
" - 置信度Confidence: 0.556\n",
266-
" - 支持度Support: 15\n",
267-
"\n",
268-
"Rule: 买了milk，又买bread\n",
269-
" - 置信度Confidence: 0.286\n",
270-
" - 支持度Support: 14\n",
269+
" - 置信度Confidence: 0.488\n",
270+
" - 支持度Support: 21\n",
271271
"\n",
272272
"Rule: 买了bananas，又买cheese\n",
273-
" - 置信度Confidence: 0.361\n",
274-
" - 支持度Support: 22\n",
273+
" - 置信度Confidence: 0.475\n",
274+
" - 支持度Support: 29\n",
275275
"\n",
276-
"Rule: 买了bread，又买apples\n",
277-
" - 置信度Confidence: 0.222\n",
278-
" - 支持度Support: 6\n",
276+
"Rule: 买了milk，又买bread\n",
277+
" - 置信度Confidence: 0.500\n",
278+
" - 支持度Support: 23\n",
279279
"\n",
280-
"Rule: 买了apples，又买bananas\n",
281-
" - 置信度Confidence: 0.606\n",
280+
"Rule: 买了bananas，又买milk\n",
281+
" - 置信度Confidence: 0.328\n",
282282
" - 支持度Support: 20\n",
283283
"\n",
284284
"Rule: 买了bread，又买cheese\n",
285-
" - 置信度Confidence: 0.296\n",
286-
" - 支持度Support: 8\n",
285+
" - 置信度Confidence: 0.093\n",
286+
" - 支持度Support: 4\n",
287287
"\n",
288288
"Rule: 买了bananas，又买bread\n",
289-
" - 置信度Confidence: 0.246\n",
290-
" - 支持度Support: 15\n",
289+
" - 置信度Confidence: 0.344\n",
290+
" - 支持度Support: 21\n",
291291
"\n"
292292
]
293293
}
@@ -314,8 +314,8 @@
314314
"output_type": "stream",
315315
"text": [
316316
"Rule: 买了milk，又买apples\n",
317-
" - 置信度Confidence: 0.184\n",
318-
" - 支持度Support: 9\n",
317+
" - 置信度Confidence: 0.326\n",
318+
" - 支持度Support: 15\n",
319319
"\n"
320320
]
321321
}
@@ -347,26 +347,26 @@
347347
"name": "stdout",
348348
"output_type": "stream",
349349
"text": [
350-
"[((0, 1), 14),\n",
351-
" ((1, 2), 10),\n",
352-
" ((3, 2), 18),\n",
353-
" ((1, 3), 9),\n",
354-
" ((0, 2), 8),\n",
355-
" ((3, 0), 6),\n",
356-
" ((3, 4), 20),\n",
357-
" ((3, 1), 9),\n",
358-
" ((1, 4), 25),\n",
359-
" ((2, 4), 22),\n",
360-
" ((2, 0), 8),\n",
361-
" ((2, 3), 18),\n",
362-
" ((2, 1), 10),\n",
363-
" ((4, 3), 20),\n",
364-
" ((0, 4), 15),\n",
365-
" ((4, 2), 22),\n",
366-
" ((0, 3), 6),\n",
367-
" ((4, 1), 25),\n",
368-
" ((1, 0), 14),\n",
369-
" ((4, 0), 15)]\n"
350+
"[((1, 2), 8),\n",
351+
" ((0, 1), 23),\n",
352+
" ((3, 2), 19),\n",
353+
" ((1, 3), 15),\n",
354+
" ((3, 0), 11),\n",
355+
" ((4, 1), 20),\n",
356+
" ((3, 1), 15),\n",
357+
" ((1, 4), 20),\n",
358+
" ((0, 2), 4),\n",
359+
" ((2, 0), 4),\n",
360+
" ((2, 3), 19),\n",
361+
" ((2, 1), 8),\n",
362+
" ((4, 3), 24),\n",
363+
" ((0, 4), 21),\n",
364+
" ((1, 0), 23),\n",
365+
" ((4, 2), 29),\n",
366+
" ((0, 3), 11),\n",
367+
" ((3, 4), 24),\n",
368+
" ((2, 4), 29),\n",
369+
" ((4, 0), 21)]\n"
370370
]
371371
}
372372
],
@@ -388,29 +388,29 @@
388388
"output_type": "stream",
389389
"text": [
390390
"Rule #1\n",
391-
"Rule: 买了apples，又买bananas\n",
392-
" - 置信度Confidence: 0.606\n",
393-
" - 支持度Support: 20\n",
391+
"Rule: 买了cheese，又买bananas\n",
392+
" - 置信度Confidence: 0.806\n",
393+
" - 支持度Support: 29\n",
394394
"\n",
395395
"Rule #2\n",
396-
"Rule: 买了cheese，又买bananas\n",
397-
" - 置信度Confidence: 0.564\n",
398-
" - 支持度Support: 22\n",
396+
"Rule: 买了apples，又买bananas\n",
397+
" - 置信度Confidence: 0.615\n",
398+
" - 支持度Support: 24\n",
399399
"\n",
400400
"Rule #3\n",
401-
"Rule: 买了bread，又买bananas\n",
402-
" - 置信度Confidence: 0.556\n",
403-
" - 支持度Support: 15\n",
401+
"Rule: 买了bread，又买milk\n",
402+
" - 置信度Confidence: 0.535\n",
403+
" - 支持度Support: 23\n",
404404
"\n",
405405
"Rule #4\n",
406-
"Rule: 买了apples，又买cheese\n",
407-
" - 置信度Confidence: 0.545\n",
408-
" - 支持度Support: 18\n",
406+
"Rule: 买了cheese，又买apples\n",
407+
" - 置信度Confidence: 0.528\n",
408+
" - 支持度Support: 19\n",
409409
"\n",
410410
"Rule #5\n",
411-
"Rule: 买了bread，又买milk\n",
412-
" - 置信度Confidence: 0.519\n",
413-
" - 支持度Support: 14\n",
411+
"Rule: 买了milk，又买bread\n",
412+
" - 置信度Confidence: 0.500\n",
413+
" - 支持度Support: 23\n",
414414
"\n"
415415
]
416416
}
@@ -676,7 +676,7 @@
676676
"output_type": "stream",
677677
"text": [
678678
"The best model is based on variable 2 and has error 37.00\n",
679-
"{'predictor': {0: 0, 1: 2}, 'variable': 2}\n"
679+
"{'variable': 2, 'predictor': {0: 0, 1: 2}}\n"
680680
]
681681
}
682682
],

‎《Python数据挖掘入门与实践》/affinity_dataset.txt

Lines changed: 0 additions & 100 deletions
This file was deleted.

0 commit comments

Comments
 (0)