pushing files to the repo from the example!
Browse files- README.md +1 -1
- init_repo_MLstructureMining.py +8 -14
- labels.csv +11 -0
README.md
CHANGED
|
@@ -185,7 +185,7 @@ The model is trained with below hyperparameters.
|
|
| 185 |
|
| 186 |
The model plot is below.
|
| 187 |
|
| 188 |
-
<style>#sk-
|
| 189 |
|
| 190 |
## Evaluation Results
|
| 191 |
|
|
|
|
| 185 |
|
| 186 |
The model plot is below.
|
| 187 |
|
| 188 |
+
<style>#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 {color: black;background-color: white;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 pre{padding: 0;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-toggleable {background-color: white;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 label.sk-toggleable__label-arrow:before {content: "▸";float: left;margin-right: 0.25em;color: #696969;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: "▾";}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-estimator:hover {background-color: #d4ebff;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-parallel-item::after {content: "";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-serial::before {content: "";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-item {z-index: 1;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-parallel::before {content: "";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 2em;bottom: 0;left: 50%;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-parallel-item {display: flex;flex-direction: column;position: relative;background-color: white;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-parallel-item:only-child::after {width: 0;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;position: relative;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-label label {font-family: monospace;font-weight: bold;background-color: white;display: inline-block;line-height: 1.2em;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-label-container {position: relative;z-index: 2;text-align: center;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67 div.sk-text-repr-fallback {display: none;}</style><div id="sk-155c4ebd-3ff3-4878-a6ed-b467111c8e67" class="sk-top-container" style="overflow: auto;"><div class="sk-text-repr-fallback"><pre>XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,colsample_bynode=1, colsample_bytree=1, enable_categorical=False,gamma=0, gpu_id=-1, importance_type=None,interaction_constraints='', learning_rate=0.300000012,max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,monotone_constraints='()', n_estimators=100, n_jobs=8,num_parallel_tree=1, predictor='auto', random_state=0,reg_alpha=0, reg_lambda=1, scale_pos_weight=None, subsample=1,tree_method='auto', validate_parameters=1, verbosity=None)</pre><b>Please rerun this cell to show the HTML repr or trust the notebook.</b></div><div class="sk-container" hidden><div class="sk-item"><div class="sk-estimator sk-toggleable"><input class="sk-toggleable__control sk-hidden--visually" id="15187887-3eef-43d1-af97-9d744586ed11" type="checkbox" checked><label for="15187887-3eef-43d1-af97-9d744586ed11" class="sk-toggleable__label sk-toggleable__label-arrow">XGBClassifier</label><div class="sk-toggleable__content"><pre>XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,colsample_bynode=1, colsample_bytree=1, enable_categorical=False,gamma=0, gpu_id=-1, importance_type=None,interaction_constraints='', learning_rate=0.300000012,max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,monotone_constraints='()', n_estimators=100, n_jobs=8,num_parallel_tree=1, predictor='auto', random_state=0,reg_alpha=0, reg_lambda=1, scale_pos_weight=None, subsample=1,tree_method='auto', validate_parameters=1, verbosity=None)</pre></div></div></div></div></div>
|
| 189 |
|
| 190 |
## Evaluation Results
|
| 191 |
|
init_repo_MLstructureMining.py
CHANGED
|
@@ -18,6 +18,11 @@ from sklearn.model_selection import HalvingGridSearchCV, train_test_split
|
|
| 18 |
import shutil
|
| 19 |
from skops import card, hub_utils
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
# Data
|
| 22 |
X, y = load_breast_cancer(as_frame=True, return_X_y=True)
|
| 23 |
X_train, X_test, y_train, y_test = train_test_split(
|
|
@@ -32,21 +37,10 @@ param_grid = {
|
|
| 32 |
"max_depth": [2, 5, 10],
|
| 33 |
}
|
| 34 |
|
| 35 |
-
# model = HalvingGridSearchCV(
|
| 36 |
-
# estimator=HistGradientBoostingClassifier(),
|
| 37 |
-
# param_grid=param_grid,
|
| 38 |
-
# random_state=42,
|
| 39 |
-
# n_jobs=-1,
|
| 40 |
-
# ).fit(X_train, y_train)
|
| 41 |
-
# model.score(X_test, y_test)# The file name is not significant, here we choose to save it with a `pkl`
|
| 42 |
-
# # extension.
|
| 43 |
|
| 44 |
-
# _, pkl_name = mkstemp(prefix="skops-", suffix=".pkl")
|
| 45 |
-
# with open(pkl_name, mode="bw") as f:
|
| 46 |
-
# pickle.dump(model, file=f)
|
| 47 |
|
| 48 |
booster = xgboost.Booster({'nthread': 8})
|
| 49 |
-
booster.load_model(
|
| 50 |
|
| 51 |
model = XGBClassifier()
|
| 52 |
|
|
@@ -55,13 +49,13 @@ model._Booster = booster
|
|
| 55 |
|
| 56 |
local_repo = mkdtemp(prefix="skops-")
|
| 57 |
hub_utils.init(
|
| 58 |
-
|
| 59 |
-
model="xgb_model_bayse_optimization_00000.bin",
|
| 60 |
requirements=[f"scikit-learn={sklearn.__version__}", f"xgboost={xgboost.__version__}"],
|
| 61 |
dst=local_repo,
|
| 62 |
task="tabular-classification",
|
| 63 |
data=X_test,
|
| 64 |
)
|
|
|
|
| 65 |
if "__file__" in locals(): # __file__ not defined during docs built
|
| 66 |
# Add this script itself to the files to be uploaded for reproducibility
|
| 67 |
hub_utils.add_files(__file__, dst=local_repo)
|
|
|
|
| 18 |
import shutil
|
| 19 |
from skops import card, hub_utils
|
| 20 |
|
| 21 |
+
# Paths
|
| 22 |
+
model_path = "xgb_model_bayse_optimization_00000.bin"
|
| 23 |
+
label_path = "labels.csv"
|
| 24 |
+
|
| 25 |
+
|
| 26 |
# Data
|
| 27 |
X, y = load_breast_cancer(as_frame=True, return_X_y=True)
|
| 28 |
X_train, X_test, y_train, y_test = train_test_split(
|
|
|
|
| 37 |
"max_depth": [2, 5, 10],
|
| 38 |
}
|
| 39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
booster = xgboost.Booster({'nthread': 8})
|
| 43 |
+
booster.load_model(model_path)
|
| 44 |
|
| 45 |
model = XGBClassifier()
|
| 46 |
|
|
|
|
| 49 |
|
| 50 |
local_repo = mkdtemp(prefix="skops-")
|
| 51 |
hub_utils.init(
|
| 52 |
+
model=model_path,
|
|
|
|
| 53 |
requirements=[f"scikit-learn={sklearn.__version__}", f"xgboost={xgboost.__version__}"],
|
| 54 |
dst=local_repo,
|
| 55 |
task="tabular-classification",
|
| 56 |
data=X_test,
|
| 57 |
)
|
| 58 |
+
shutil.copy(label_path, os.path.join(local_repo, label_path))
|
| 59 |
if "__file__" in locals(): # __file__ not defined during docs built
|
| 60 |
# Add this script itself to the files to be uploaded for reproducibility
|
| 61 |
hub_utils.add_files(__file__, dst=local_repo)
|
labels.csv
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
,Label,Similar
|
| 2 |
+
0,1000017.csv,"['1000032.csv', '1000059.csv']"
|
| 3 |
+
1,1000024.csv,
|
| 4 |
+
2,1000035.csv,
|
| 5 |
+
3,1000058.csv,
|
| 6 |
+
4,1000060.csv,
|
| 7 |
+
5,1000061.csv,
|
| 8 |
+
6,1000062.csv,
|
| 9 |
+
7,1000063.csv,
|
| 10 |
+
8,1000094.csv,
|
| 11 |
+
9,1000096.csv,
|