Skip to content

Assessment fix #210

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 8, 2025
Merged

Assessment fix #210

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
99044c6
fixed assessment metrics
samyarpotlapalli Apr 1, 2025
294ed96
fix: update write_json_files and examples to properly generate ROC ch…
djm21 Apr 8, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions examples/pzmm_binary_classification_model_import.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -717,7 +717,7 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": null,
"metadata": {
"Collapsed": "false"
},
Expand Down Expand Up @@ -751,8 +751,7 @@
" \n",
" # Calculate the model statistics, ROC chart, and Lift chart; then write to json files\n",
" pzmm.JSONFiles.calculate_model_statistics(\n",
" target_value=1, \n",
" prob_value=0.5, \n",
" target_value=1,\n",
" train_data=train_data, \n",
" test_data=test_data, \n",
" json_path=path\n",
Expand Down
5 changes: 2 additions & 3 deletions examples/pzmm_generate_complete_model_card.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -874,8 +874,7 @@
"source": [
"# Step 10: Write model statistics files\n",
"pzmm.JSONFiles.calculate_model_statistics(\n",
" target_value=1, \n",
" prob_value=0.5, \n",
" target_value=1,\n",
" train_data=train_scored[[target, ti, t1]], \n",
" test_data=test_scored[[target, ti, t1]],\n",
" validate_data=test_scored[[target, ti, t1]],\n",
Expand Down Expand Up @@ -1786,7 +1785,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": ".venv",
"language": "python",
"name": "python3"
},
Expand Down
32 changes: 15 additions & 17 deletions src/sasctl/pzmm/write_json_files.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,7 @@ def write_var_json(

@staticmethod
def generate_variable_properties(
input_data: Union[DataFrame, Series]
input_data: Union[DataFrame, Series],
) -> List[dict]:
"""
Generate a list of dictionaries of variable properties given an input dataframe.
Expand Down Expand Up @@ -1192,7 +1192,6 @@ def bias_dataframes_to_json(
def calculate_model_statistics(
cls,
target_value: Union[str, int, float],
prob_value: Union[int, float, None] = None,
validate_data: Union[DataFrame, List[list], Type["numpy.ndarray"]] = None,
train_data: Union[DataFrame, List[list], Type["numpy.ndarray"]] = None,
test_data: Union[DataFrame, List[list], Type["numpy.ndarray"]] = None,
Expand All @@ -1211,8 +1210,7 @@ def calculate_model_statistics(
Datasets must contain the actual and predicted values and may optionally contain
the predicted probabilities. If no probabilities are provided, a dummy
probability dataset is generated based on the predicted values and normalized by
the target value. If a probability threshold value is not provided, the
threshold value is set at 0.5.
the target value.

Datasets can be provided in the following forms, with the assumption that data
is ordered as `actual`, `predict`, and `probability` respectively:
Expand All @@ -1229,9 +1227,6 @@ def calculate_model_statistics(
----------
target_value : str, int, or float
Target event value for model prediction events.
prob_value : int or float, optional
The threshold value for model predictions to indicate an event occurred. The
default value is 0.5.
validate_data : pandas.DataFrame, list of list, or numpy.ndarray, optional
Dataset pertaining to the validation data. The default value is None.
train_data : pandas.DataFrame, list of list, or numpy.ndarray, optional
Expand Down Expand Up @@ -1284,30 +1279,33 @@ def calculate_model_statistics(
continue

data = cls.stat_dataset_to_dataframe(data, target_value, target_type)
data["predict_proba2"] = 1 - data["predict_proba"]

conn.upload(
data,
casout={"name": "assess_dataset", "replace": True, "caslib": "Public"},
casout={"caslib": "Public", "name": "assess_dataset", "replace": True},
)

if target_type == "classification":
conn.percentile.assess(
table={"name": "assess_dataset", "caslib": "Public"},
response="predict",
pVar="predict_proba",
event=str(target_value),
pEvent=str(prob_value) if prob_value else str(0.5),
inputs="actual",
inputs="predict_proba",
response="actual",
event="1",
pvar="predict_proba2",
pevent="0",
includeLift=True,
fitStatOut={"name": "FitStat", "replace": True, "caslib": "Public"},
rocOut={"name": "ROC", "replace": True, "caslib": "Public"},
casout={"name": "Lift", "replace": True, "caslib": "Public"},
)
else:
conn.percentile.assess(
table={"name": "assess_dataset", "caslib": "Public"},
response="predict",
inputs="actual",
fitStatOut={"name": "FitStat", "replace": True, "caslib": "Public"},
casout={"name": "Lift", "replace": True, "caslib": "Public"},
response="actual",
inputs="predict",
fitStatOut={"caslib": "Public", "name": "FitStat", "replace": True},
casout={"caslib": "Public", "name": "Lift", "replace": True},
)

fitstat_dict = (
Expand Down
Loading