metrics
apk(actual, predicted, k=10)
¶
Computes the average precision at k. This function computes the average precision at k between two lists of items.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
actual |
list
|
A list of elements that are to be predicted (order doesn’t matter) |
required |
predicted |
list
|
A list of predicted elements (order does matter) |
required |
k |
int
|
The maximum number of predicted elements |
10
|
Returns:
Name | Type | Description |
---|---|---|
score |
float
|
The average precision at k over the input lists |
Source code in spotpython/utils/metrics.py
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 |
|
calculate_xai_consistency_corr(attributions)
¶
Calculates the consistency of XAI methods by computing the mean of the upper triangle of the correlation matrix of the provided attributions.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
attributions |
ndarray
|
Array of shape (n_methods, n_features) containing the attributions from different XAI methods. |
required |
Returns:
Name | Type | Description |
---|---|---|
float |
float
|
Mean value of the upper triangle of the correlation matrix. |
Source code in spotpython/utils/metrics.py
203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 |
|
calculate_xai_consistency_cosine(attributions)
¶
Calculates the consistency of XAI methods by computing the mean of the upper triangle of the cosine similarity matrix of the provided attributions.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
attributions |
ndarray
|
Array of shape (n_methods, n_features) containing the attributions from different XAI methods. |
required |
Returns:
Name | Type | Description |
---|---|---|
float |
float
|
Mean value of the upper triangle of the cosine similarity matrix. |
Source code in spotpython/utils/metrics.py
229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
calculate_xai_consistency_euclidean(attributions)
¶
Calculates the consistency of XAI methods by computing the mean of the upper triangle of the Euclidean distance matrix of the provided attributions.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
attributions |
ndarray
|
Array of shape (n_methods, n_features) containing the attributions from different XAI methods. |
required |
Returns:
Name | Type | Description |
---|---|---|
float |
float
|
Mean value of the upper triangle of the Euclidean distance matrix. |
Source code in spotpython/utils/metrics.py
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 |
|
calculate_xai_consistency_spearman(attributions)
¶
Calculates the consistency of XAI methods using Spearman rank correlation.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
attributions |
ndarray
|
shape (n_methods, n_features) |
required |
Returns:
Name | Type | Description |
---|---|---|
float |
float
|
Mean of upper triangle of Spearman correlation matrix (excluding diagonal) |
Source code in spotpython/utils/metrics.py
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 |
|
get_metric_sign(metric_name)
¶
Returns the sign of a metric.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
metric_name |
str
|
The name of the metric. Can be one of the following: - “accuracy_score” - “cohen_kappa_score” - “f1_score” - “hamming_loss” - “hinge_loss” -“jaccard_score” - “matthews_corrcoef” - “precision_score” - “recall_score” - “roc_auc_score” - “zero_one_loss” |
required |
Returns:
Name | Type | Description |
---|---|---|
sign |
float
|
The sign of the metric. -1 for max, +1 for min. |
Raises:
Type | Description |
---|---|
ValueError
|
If the metric is not found. |
Examples:
>>> from spotpython.metrics import get_metric_sign
>>> get_metric_sign("accuracy_score")
-1
>>> get_metric_sign("hamming_loss")
+1
Source code in spotpython/utils/metrics.py
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 |
|
mapk(actual, predicted, k=10)
¶
Computes the mean average precision at k. This function computes the mean average precision at k between two lists of lists of items.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
actual |
list
|
A list of lists of elements that are to be predicted (order doesn’t matter in the lists) |
required |
predicted |
list
|
A list of lists of predicted elements (order matters in the lists) |
required |
k |
int
|
The maximum number of predicted elements |
10
|
Returns:
Name | Type | Description |
---|---|---|
score |
float
|
The mean average precision at k over the input lists |
Source code in spotpython/utils/metrics.py
64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
|
mapk_score(y_true, y_pred, k=3)
¶
Wrapper for mapk func using numpy arrays
Args: y_true (np.array): array of true values y_pred (np.array): array of predicted values k (int): number of predictions
Returns:
Name | Type | Description |
---|---|---|
score |
float
|
mean average precision at k |
Examples:
>>> y_true = np.array([0, 1, 2, 2])
>>> y_pred = np.array([[0.5, 0.2, 0.2], # 0 is in top 2
[0.3, 0.4, 0.2], # 1 is in top 2
[0.2, 0.4, 0.3], # 2 is in top 2
[0.7, 0.2, 0.1]]) # 2 isn't in top 2
>>> mapk_score(y_true, y_pred, k=1)
0.25
>>> mapk_score(y_true, y_pred, k=2)
0.375
>>> mapk_score(y_true, y_pred, k=3)
0.4583333333333333
>>> mapk_score(y_true, y_pred, k=4)
0.4583333333333333
Source code in spotpython/utils/metrics.py
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 |
|
mapk_scorer(estimator, X, y)
¶
Scorer for mean average precision at k. This function computes the mean average precision at k between two lists of lists of items.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
estimator |
sklearn estimator
|
The estimator to be used for prediction. |
required |
X |
array-like of shape (n_samples, n_features
|
The input samples. |
required |
y |
array-like of shape (n_samples,
|
The target values. |
required |
Returns:
Name | Type | Description |
---|---|---|
score |
float
|
The mean average precision at k over the input lists |
Source code in spotpython/utils/metrics.py
116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 |
|