def useLRtoPredictScore(targetFileName, exam_mark=None, needNorm=True):
if exam_mark is None:
exam_mark = DATA_MARK
_file_Relative_Path = os.path.join(exam_mark, targetFileName)
student_data, headerArray = load_data_from_file(_file_Relative_Path)
_score_map = get_final_score_map()
_score_array = []
for _student_record in student_data:
_score_array.append(_score_map[_student_record[0]])
targetFeatureIndexArray = [i for i in range(1, headerArray.__len__())]
featureMatrix = getSerevalColumn(student_data, targetFeatureIndexArray)
if needNorm:
featureMatrix = normizeMatrix(featureMatrix)
_lr = LinearRegression(fit_intercept=True)
_lr.fit(featureMatrix, _score_array)
y_predicted = _lr.predict(featureMatrix)
# y_predicted.astype(int)
print()
# print(headerArray);
# print(_lr.coef_)
# print(_lr.intercept_)
print(getprecisionWithTorlerate(y_predicted, _score_array, 0.5),
getprecisionWithTorlerate(y_predicted, _score_array, 1.5),
getprecisionWithTorlerate(y_predicted, _score_array, 2.5),
spearmanr(y_predicted, _score_array),
r2_score(_score_array, y_predicted))
def useElaticNettoPredictScoreWithKFold(targetFileName,
exam_mark=None,
needNorm=True):
if exam_mark is None:
exam_mark = DATA_MARK
featureMatrix, _score_array = getDataAndScore(targetFileName, exam_mark)
if needNorm:
featureMatrix = normizeMatrix(featureMatrix)
_lr = ElasticNetCV(alphas=[0.0001, 0.0005, 0.001, 0.01, 0.1, 1, 10],
l1_ratio=[1e-4, .01, .1, .5, .9, .99],
max_iter=5000,
cv=model_selection.StratifiedKFold(5, shuffle=True))
precision_array = []
for _index in range(10):
_scores = model_selection.cross_val_score(
_lr,
featureMatrix,
_score_array,
cv=model_selection.StratifiedKFold(5, shuffle=True),
scoring=lr_precision)
precision_array.append(_scores.mean())
print(np.array(precision_array).mean())
def useLRtoPredictScoreWithKFold(targetFileName,
exam_mark=None,
needNorm=True):
if exam_mark is None:
exam_mark = DATA_MARK
featureMatrix, _score_array = getDataAndScore(targetFileName, exam_mark)
if needNorm:
featureMatrix = normizeMatrix(featureMatrix)
_lr = LinearRegression(fit_intercept=True)
precision_array = []
for _index in range(10):
_scores = model_selection.cross_val_score(
_lr,
featureMatrix,
_score_array,
cv=model_selection.StratifiedKFold(5, shuffle=True),
scoring=lr_precision)
precision_array.append(_scores.mean())
print(np.array(precision_array).mean())
def useLassotoPredictScoreWithKFold(targetFileName,
exam_mark=None,
needNorm=True):
if exam_mark is None:
exam_mark = DATA_MARK
featureMatrix, _score_array = getDataAndScore(targetFileName, exam_mark)
if needNorm:
featureMatrix = normizeMatrix(featureMatrix)
_lr = LassoCV(alphas=[0.01, 0.05, 0.1, 0.5, 1, 10],
cv=model_selection.StratifiedKFold(5, shuffle=True),
tol=1e-4)
precision_array = []
for _index in range(10):
_scores = model_selection.cross_val_score(
_lr,
featureMatrix,
_score_array,
cv=model_selection.StratifiedKFold(5, shuffle=True),
scoring=lr_precision)
precision_array.append(_scores.mean())
print(np.array(precision_array).mean())