forked from wubingpei/Decision-Tree
-
Notifications
You must be signed in to change notification settings - Fork 0
/
functions.cpp
372 lines (357 loc) · 9.85 KB
/
functions.cpp
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
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
#include "header.h"
/*
* Parses a string and stores data
* into a vector of vector of strings
*/
void parse(string& someString, vvs &attributeTable)
{
int attributeCount = 0;
vs vectorOfStrings;
while (someString.length() != 0 && someString.find(',') != string::npos)
{
size_t pos;
string singleAttribute;
pos = someString.find_first_of(',');
singleAttribute = someString.substr(0, pos);
vectorOfStrings.push_back(singleAttribute);
someString.erase(0, pos+1);
}
vectorOfStrings.push_back(someString);
attributeTable.push_back(vectorOfStrings);
vectorOfStrings.clear();
}
/*
* Prints a vector of vector of strings
* For debugging purposes only.
*/
void printAttributeTable(vvs &attributeTable)
{
int inner, outer;
for (outer = 0; outer < attributeTable.size(); outer++) {
for (inner = 0; inner < attributeTable[outer].size(); inner++) {
cout << attributeTable[outer][inner] << "\t";
}
cout << endl;
}
}
/*
* Prunes a table based on a column/attribute's name
* and value of that attribute. Removes that column
* and all rows that have that value for that column.
*/
vvs pruneTable(vvs &attributeTable, string &colName, string value)
{
int iii, jjj;
vvs prunedTable;
int column = -1;
vs headerRow;
for (iii = 0; iii < attributeTable[0].size(); iii++) {
if (attributeTable[0][iii] == colName) {
column = iii;
break;
}
}
for (iii = 0; iii < attributeTable[0].size(); iii++) {
if (iii != column) {
headerRow.push_back(attributeTable[0][iii]);
}
}
prunedTable.push_back(headerRow);
for (iii = 0; iii < attributeTable.size(); iii++) {
vs auxRow;
if (attributeTable[iii][column] == value) {
for (jjj = 0; jjj < attributeTable[iii].size(); jjj++) {
if(jjj != column) {
auxRow.push_back(attributeTable[iii][jjj]);
}
}
prunedTable.push_back(auxRow);
}
}
return prunedTable;
}
/*
* Recursively builds the decision tree based on
* the data that it is passed and tha table info.
*/
node* buildDecisionTree(vvs &table, node* nodePtr, vvs &tableInfo)
{
if (tableIsEmpty(table)) {
return NULL;
}
if (isHomogeneous(table)) {
nodePtr->isLeaf = true;
nodePtr->label = table[1][table[1].size()-1];
return nodePtr;
} else {
string splittingCol = decideSplittingColumn(table);
nodePtr->splitOn = splittingCol;
int colIndex = returnColumnIndex(splittingCol, tableInfo);
int iii;
for (iii = 1; iii < tableInfo[colIndex].size(); iii++) {
node* newNode = (node*) new node;
newNode->label = tableInfo[colIndex][iii];
nodePtr->childrenValues.push_back(tableInfo[colIndex][iii]);
newNode->isLeaf = false;
newNode->splitOn = splittingCol;
vvs auxTable = pruneTable(table, splittingCol, tableInfo[colIndex][iii]);
nodePtr->children.push_back(buildDecisionTree(auxTable, newNode, tableInfo));
}
}
return nodePtr;
}
/*
* Returns true if all rows in a subtable
* have the same class label.
* This means that that node's class label
* has been decided.
*/
bool isHomogeneous(vvs &table)
{
int iii;
int lastCol = table[0].size() - 1;
string firstValue = table[1][lastCol];
for (iii = 1; iii < table.size(); iii++) {
if (firstValue != table[iii][lastCol]) {
return false;
}
}
return true;
}
/*
* Returns a vector of integers containing the counts
* of all the various values of an attribute/column.
*/
vi countDistinct(vvs &table, int column)
{
vs vectorOfStrings;
vi counts;
bool found = false;
int foundIndex;
for (int iii = 1; iii < table.size(); iii++) {
for (int jjj = 0; jjj < vectorOfStrings.size(); jjj++) {
if (vectorOfStrings[jjj] == table[iii][column]) {
found = true;
foundIndex = jjj;
break;
} else {
found = false;
}
}
if (!found) {
counts.push_back(1);
vectorOfStrings.push_back(table[iii][column]);
} else {
counts[foundIndex]++;
}
}
int sum = 0;
for (int iii = 0; iii < counts.size(); iii++) {
sum += counts[iii];
}
counts.push_back(sum);
return counts;
}
/*
* Decides which column to split on
* based on entropy. Returns the column
* with the least entropy.
*/
string decideSplittingColumn(vvs &table)
{
int column, iii;
double minEntropy = DBL_MAX;
int splittingColumn = 0;
vi entropies;
for (column = 0; column < table[0].size() - 1; column++) {
string colName = table[0][column];
msi tempMap;
vi counts = countDistinct(table, column);
vd attributeEntropy;
double columnEntropy = 0.0;
for (iii = 1; iii < table.size()-1; iii++) {
double entropy = 0.0;
if (tempMap.find(table[iii][column]) != tempMap.end()) { // IF ATTRIBUTE IS ALREADY FOUND IN A COLUMN, UPDATE IT'S FREQUENCY
tempMap[table[iii][column]]++;
} else { // IF ATTRIBUTE IS FOUND FOR THE FIRST TIME IN A COLUMN, THEN PROCESS IT AND CALCULATE IT'S ENTROPY
tempMap[table[iii][column]] = 1;
vvs tempTable = pruneTable(table, colName, table[iii][column]);
vi classCounts = countDistinct(tempTable, tempTable[0].size()-1);
int jjj, kkk;
for (jjj = 0; jjj < classCounts.size(); jjj++) {
double temp = (double) classCounts[jjj];
entropy -= (temp/classCounts[classCounts.size()-1])*(log(temp/classCounts[classCounts.size()-1]) / log(2));
}
attributeEntropy.push_back(entropy);
entropy = 0.0;
}
}
for (iii = 0; iii < counts.size() - 1; iii++) {
columnEntropy += ((double) counts[iii] * (double) attributeEntropy[iii]);
}
columnEntropy = columnEntropy / ((double) counts[counts.size() - 1]);
if (columnEntropy <= minEntropy) {
minEntropy = columnEntropy;
splittingColumn = column;
}
}
return table[0][splittingColumn];
}
/*
* Returns an integer which is the
* index of a column passed as a string
*/
int returnColumnIndex(string &columnName, vvs &tableInfo)
{
int iii;
for (iii = 0; iii < tableInfo.size(); iii++) {
if (tableInfo[iii][0] == columnName) {
return iii;
}
}
return -1;
}
/*
* Returns true if the table is empty
* returns false otherwise
*/
bool tableIsEmpty(vvs &table)
{
return (table.size() == 1);
}
/*
* Recursively prints the decision tree
* For debugging purposes only
*/
void printDecisionTree(node* nodePtr)
{
if(nodePtr == NULL) {
return;
}
if (!nodePtr->children.empty()) {
cout << " Value: " << nodePtr->label << endl;
cout << "Split on: " << nodePtr->splitOn;
int iii;
for (iii = 0; iii < nodePtr->children.size(); iii++) {
cout << "\t";
printDecisionTree(nodePtr->children[iii]);
}
return;
} else {
cout << "Predicted class = " << nodePtr->label;
return;
}
}
/*
* Takes a row and traverses that row through
* the decision tree to find out the
* predicted class label. If none is found
* returns the default class label which is
* the class label with the highest frequency.
*/
string testDataOnDecisionTree(vs &singleLine, node* nodePtr, vvs &tableInfo, string defaultClass)
{
string prediction;
while (nodePtr->isLeaf != true && !nodePtr->children.empty()) {
int index = returnColumnIndex(nodePtr->splitOn, tableInfo);
string value = singleLine[index];
int childIndex = returnIndexOfVector(nodePtr->childrenValues, value);
nodePtr = nodePtr->children[childIndex];
if (nodePtr == NULL) {
prediction = defaultClass;
break;
}
prediction = nodePtr->label;
}
return prediction;
}
/*
* Returns an integer which is the index
* of a string in a vector of strings
*/
int returnIndexOfVector(vs &stringVector, string value)
{
int iii;
for (iii = 0; iii < stringVector.size(); iii++) {
if (stringVector[iii] == value) {
return iii;
}
}
return -1;
}
/*
* Outputs the predictions to file
* and returns the accuracy of the classification
*/
double printPredictionsAndCalculateAccuracy(vs &givenData, vs &predictions)
{
ofstream outputFile;
outputFile.open("decisionTreeOutput.txt");
int correct = 0;
outputFile << setw(3) << "#" << setw(16) << "Given Class" << setw(31) << right << "Predicted Class" << endl;
outputFile << "--------------------------------------------------" << endl;
for (int iii = 0; iii < givenData.size(); iii++) {
outputFile << setw(3) << iii+1 << setw(16) << givenData[iii];
if (givenData[iii] == predictions[iii]) {
correct++;
outputFile << " ------------ ";
} else {
outputFile << " xxxxxxxxxxxx ";
}
outputFile << predictions[iii] << endl;
}
outputFile << "--------------------------------------------------" << endl;
outputFile << "Total number of instances in test data = " << givenData.size() << endl;
outputFile << "Number of correctly predicted instances = " << correct << endl;
outputFile.close();
return (double) correct/50 * 100;
}
/*
* Returns a vvs which contains information about
* the data table. The vvs contains the names of
* all the columns and the values that each
* column can take
*/
vvs generateTableInfo(vvs &dataTable)
{
vvs tableInfo;
for (int iii = 0; iii < dataTable[0].size(); iii++) {
vs tempInfo;
msi tempMap;
for (int jjj = 0; jjj < dataTable.size(); jjj++) {
if (tempMap.count(dataTable[jjj][iii]) == 0) {
tempMap[dataTable[jjj][iii]] = 1;
tempInfo.push_back(dataTable[jjj][iii]);
} else {
tempMap[dataTable[jjj][iii]]++;
}
}
tableInfo.push_back(tempInfo);
}
return tableInfo;
}
/*
* Returns the most frequent class from the training data
* This class will be used as the default class label
*/
string returnMostFrequentClass(vvs &dataTable)
{
msi trainingClasses; // Stores the classlabels and their frequency
for (int iii = 1; iii < dataTable.size(); iii++) {
if (trainingClasses.count(dataTable[iii][dataTable[0].size()-1]) == 0) {
trainingClasses[dataTable[iii][dataTable[0].size()-1]] = 1;
} else {
trainingClasses[dataTable[iii][dataTable[0].size()-1]]++;
}
}
msi::iterator mapIter;
int highestClassCount = 0;
string mostFrequentClass;
for (mapIter = trainingClasses.begin(); mapIter != trainingClasses.end(); mapIter++) {
if (mapIter->second >= highestClassCount) {
highestClassCount = mapIter->second;
mostFrequentClass = mapIter->first;
}
}
return mostFrequentClass;
}