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 usLRtoPredict():
examId_List = ["e1", "e2", "e3", "e4"]
target_List = ["programStateRecord"]
print('|数据名称|预测|r^2|spearman|')
print('|-|-|-|')
for eid in examId_List:
for target in target_List:
dataFileName = eid + "-" + target
_data_matrix, _data_header, _score_array = getData("npsm//" +
dataFileName)
_feature_matrix = getSerevalColumn(
_data_matrix, [i for i in range(1, _data_header.__len__())])
# _feature_matrix = getSerevalColumn(_data_matrix,[1,8]);
# _feature_matrix = getSerevalColumn(_data_matrix,[1,4,8]);
# _feature_matrix = getSerevalColumn(_data_matrix,[1,2,3,9]);
_score_array = np.array(_score_array).reshape(
_score_array.__len__(), 1)
_lr = LinearRegression()
_lr.fit(_feature_matrix, _score_array)
y_predicted = _lr.predict(_feature_matrix)
print("|", dataFileName, "|",
getprecisionWithTorlerate(_score_array, y_predicted,
0.5), "|",
getprecisionWithTorlerate(_score_array, y_predicted,
1.5), "|",
getprecisionWithTorlerate(_score_array, y_predicted, 2.5),
"|", r2_score(_score_array, y_predicted), "|",
spearmanr(_score_array, y_predicted), "|",
getprecisionWithTorlerate(_score_array, y_predicted, 5))
def usLRtoPredictWithExpDef():
examId_List = ["e1", "e2", "e3", "e4"]
algorithm_List = ["EQ", "Watwin"]
target_List = ["finalscore"]
scoreMap = getGradeMap()
print('|数据名称|预测准确率|')
print('|-|-|')
for al in algorithm_List:
for eid in examId_List:
for target in target_List:
dataFileName = eid + "-" + al + "-" + target
student_data = getStudentData(al + "//" + dataFileName)
# scoreArray = getOneColumn(student_data, 2);
scoreArray = []
final_score_map = get_final_score_map()
scoreArray = getOneColumn(student_data, 2)
for index in range(scoreArray.__len__()):
scoreArray[index] = scoreMap[scoreArray[index]]
scoreArray = np.array(scoreArray).reshape(
scoreArray.__len__(), 1)
watwinArray = getOneColumn(student_data, 1)
watwinArray = np.array(watwinArray).reshape(
watwinArray.__len__(), 1)
_lr = LinearRegression(fit_intercept=True)
_lr.fit(watwinArray, scoreArray)
y_predicted = _lr.predict(watwinArray)
print("|", dataFileName, "|",
getprecisionWithTorlerate(y_predicted, scoreArray, 0.5),
"|")
def usLRtoPredict():
examId_List = ["e1", "e2", "e3", "e4"]
algorithm_List = ["EQ", "Watwin"]
target_List = ["finalscore"]
print('|数据名称|预测|5分|10分|')
print('|-|-|-|')
for al in algorithm_List:
for eid in examId_List:
for target in target_List:
dataFileName = eid + "-" + al + "-" + target
student_data = getStudentData(al + "//" + dataFileName)
# scoreArray = getOneColumn(student_data, 2);
scoreArray = []
final_score_map = get_final_score_map()
for _line in student_data:
scoreArray.append(final_score_map[str(_line[0])])
scoreArray = np.array(scoreArray).reshape(
scoreArray.__len__(), 1)
watwinArray = getOneColumn(student_data, 1)
watwinArray = np.array(watwinArray).reshape(
watwinArray.__len__(), 1)
_lr = LinearRegression(fit_intercept=True)
_lr.fit(watwinArray, scoreArray)
y_predicted = _lr.predict(watwinArray)
print("|", dataFileName, "|",
getprecisionWithTorlerate(y_predicted, scoreArray,
0.5), "|",
getprecisionWithTorlerate(y_predicted, scoreArray,
1.5), "|",
getprecisionWithTorlerate(y_predicted, scoreArray, 2.5),
"|", r2_score(scoreArray, y_predicted), "|",
spearmanr(y_predicted, scoreArray))
def lr_precision(_lr, x_test, y_test):
y_predict = _lr.predict(x_test)
return getprecisionWithTorlerate(y_test, y_predict, 0.5)
def getScore(_svr, x_test, y_test):
y_predict = _svr.predict(x_test)
return getprecisionWithTorlerate(y_test, y_predict, 0.5)
def usLRtoPredictWithKFold():
examId_List = ["e1", "e2", "e3", "e4"]
algorithm_List = ["EQ", "Watwin"]
target_List = ["finalscore"]
print('|数据名称|预测|5分|10分|')
print('|-|-|-|')
for al in algorithm_List:
for eid in examId_List:
for target in target_List:
dataFileName = eid + "-" + al + "-" + target
student_data = getStudentData(al + "//" + dataFileName)
# scoreArray = getOneColumn(student_data, 2);
scoreArray = []
final_score_map = get_final_score_map()
for _line in student_data:
scoreArray.append(final_score_map[str(_line[0])])
scoreArray = np.array(scoreArray).reshape(
scoreArray.__len__(), 1)
watwinArray = getOneColumn(student_data, 1)
watwinArray = np.array(watwinArray).reshape(
watwinArray.__len__(), 1)
kf = KFold(n_splits=10, shuffle=True)
accurate_array = []
within_5_array = []
r_2_array = []
within_10_array = []
for train_index_array, test_index_array in kf.split(
watwinArray):
X_train = []
X_test = []
y_train = []
y_test = []
for train_index in train_index_array:
X_train.append(watwinArray[train_index])
y_train.append(scoreArray[train_index])
for test_index in test_index_array:
X_test.append(watwinArray[test_index])
y_test.append(scoreArray[test_index])
_lr = LinearRegression(fit_intercept=True)
_lr.fit(X_train, y_train)
y_predicted = _lr.predict(X_test)
accurate_array.append(
getprecisionWithTorlerate(y_predicted, y_test, 0.5))
within_5_array.append(
getprecisionWithTorlerate(y_test, y_predicted, 1.5))
within_10_array.append(
getprecisionWithTorlerate(y_test, y_predicted, 2.5))
r_2_array.append(r2_score(y_test, y_predicted))
print("|", dataFileName, "|",
np.array(accurate_array).mean(), "|",
np.array(within_5_array).mean(), "|",
np.array(within_10_array).mean(), "|",
np.array(r_2_array).mean())