def main():
qresult = connect_db('solar.db', 'dip')
smiles, compounds, gaps = get_data(qresult)
mols = get_mols(smiles)
fps_morgan, failed_mols = get_fingerprints(mols)
refine_compounds(compounds, mols, gaps, failed_mols)
compound_array = np.array(compounds)
gaps_array = np.array(gaps)
train_id, test_id, y_train, y_test = train_test_split(compound_array,
gaps_array,
test_size=0.20,
random_state=0)
train_fps = get_fp_from_id(compounds, fps_morgan, train_id)
test_fps = get_fp_from_id(compounds, fps_morgan, test_id)
xgb1 = XGBRegressor(n_estimators=2000,
learning_rate=0.03,
max_depth=7,
colsample_bytree=0.6,
nthread=8,
scale_pos_weight=1,
gamma=0,
random_state=0,
subsample=0.6,
min_child_weight=3,
early_stopping_rounds=10,
reg_alpha=1)
modelfit(xgb1, train_fps, y_train)
#xgb1 = joblib.load('gbdt_dip_xgb.joblib')
#joblib.dump(xgb1, 'gbdt_dip_xgb2.joblib')
y_pred_cv = cvp(xgb1, train_fps, y_train, cv=4, n_jobs=8)
y_train_pred = xgb1.predict(train_fps)
y_pred_test = xgb1.predict(test_fps)
train_df = pd.DataFrame()
test_df = pd.DataFrame()
train_df['id'] = pd.Series(train_id)
train_df['dip_exp'] = pd.Series(y_train)
train_df['dip_cv'] = pd.Series(y_pred_cv)
train_df['dip_gbdt'] = pd.Series(y_train_pred)
train_df['Group'] = 'Train'
test_df['id'] = pd.Series(test_id)
test_df['dip_exp'] = pd.Series(y_test)
test_df['dip_cv'] = pd.Series(y_pred_test)
test_df['dip_gbdt'] = pd.Series(y_pred_test)
test_df['Group'] = 'Test'
result_df = pd.concat([train_df, test_df])
result_df.to_csv('dip_xgb_train_test.csv')
test_err = mean_squared_error(y_pred_test, y_test)
print('Test error: {:4f}'.format(np.sqrt(test_err)))
def scan_fit(self,X,y):
self.n_classes = len(np.unique(y))
newX,newy,scan_round_total = self._sample_slicer(X,y)
sample_vector_list = []
for estimator in self.estimators:
estimator.fit(newX, newy)
if self.k_fold > 1:# use cv
predict_ = cvp(estimator, newX, newy, cv=self.k_fold, n_jobs = -1)
else:#use oob
predict_ = estimator.oob_decision_function_
#fill default value if meet nan
inds = np.where(np.isnan(predict_))
predict_[inds] = 1./self.n_classes
sample_vector = predict_.reshape((len(X),scan_round_total*self.n_classes))
sample_vector_list.append(sample_vector)
return np.hstack(sample_vector_list)
def predict(self, X, y):
"""
Returns a generator containing the predictions for each of the
internal models (using cross_val_predict and a CV=12).
Parameters
----------
X : ndarray or DataFrame of shape n x m
A matrix of n instances with m features
y : ndarray or Series of length n
An array or series of target or class values
kwargs: dict
keyword arguments passed to Scikit-Learn API.
"""
for model in self.models:
yield cvp(model, X, y, cv=12)
def predict(self, X, y):
"""
Returns a generator containing the predictions for each of the
internal models (using cross_val_predict and a CV=12).
Parameters
----------
X : ndarray or DataFrame of shape n x m
A matrix of n instances with m features
y : ndarray or Series of length n
An array or series of target or class values
kwargs: dict
keyword arguments passed to Scikit-Learn API.
"""
for model in self.models:
yield cvp(model, X, y, cv=12)
print(set_sizes[0])
print('here', set_sizes[nrows] * 0.7)
X_train = X.head(int(set_sizes[nrows] * 0.7))
X_test = X.tail(int(set_sizes[nrows] * 0.3))
Y_train = Y.head(int(set_sizes[nrows] * 0.7))
Y_test = Y.tail(int(set_sizes[nrows] * 0.3))
ne_lr = LinearRegression(minibatches=None)
Y2 = pd.to_numeric(Y, downcast='float')
print("here", type((Y2)))
print(type(Y_train))
ne_lr.fit(X_train, pd.to_numeric(Y_train, downcast='float'))
print(ne_lr)
y_pred = ne_lr.predict(X_test)
res = mean_squared_error(Y_test, y_pred)
#res = scoring(y_target=Y_test, y_predicted=y_pred, metric='rmse')
print("results: ", res)
lin = linear_model.LinearRegression()
lin.fit(X_train, Y_train)
predictedCV = cvp(lin, X, Y, cv=10)
print("rmse cross val", mean_squared_error(Y, predictedCV))
return data
def make_matrix(l):
matrix = np.full((ROW, COL), 0)
for d in l:
matrix[d[0]][d[1]] = d[2]
return matrix
if __name__ == "__main__":
train = read_csv(TRAIN)
gender = read_csv(GENDER)
year = read_csv(YEAR)
X1 = make_matrix(train)
X2 = X1.T
Y1 = np.asarray(gender).T[0]
Y2 = np.asarray(year).T[0]
clf1 = logr()
scores = cvs(clf1, X1, Y1, cv=10)
print("Min CV error: {}".format(1 - max(scores)))
clf2 = logr(solver="saga", multi_class="multinomial")
pred = cvp(clf2, X2, Y2, cv=10)
mse1 = mse(Y2, pred)
mse2 = mse(Y2, np.full_like(Y2, np.mean(Y2)))
print("Regression MSE: {}".format(mse1))
print("Naive MSE: {}".format(mse2))
# 可以使用 Scikit-Image, Pillow, OpenCV 等等讓某些模式更為突出, 例如閉環等等 # 從這裡開始以下的輸出結果還沒有確認過(設備問題, 執行時間太長) # 多標籤分類 # 一般來說每個實例都只會被分在一個類別裡, 若希望分類器為實例分出多個標籤 # 注意: 不是所有的分類器都支援多標籤分類 from sklearn.neighbors import KNeighborsClassifier y_train_large = (y_train >= 7) # 儲存大於等於7的標籤 y_train_odd = (y_train % 2 == 1) # 儲存奇數 y_multilabel = np.c_[y_train_large, y_train_odd] knn_clf = KNeighborsClassifier() # default: n_neighbors = 5 knn_clf.fit(X_train, y_multilabel) # print(knn_clf.predict([some_digit])) # [[False False]] 2 既非大於等於7也非奇數 # 計算 f1_score y_train_knn_pred = cvp(knn_clf, X_train, y_train, cv=3) print(f1_score(y_train, y_train_knn_pred, average="macro")) # 多輸出分類 # 多標籤分類的泛化, 其標籤也可以是多種類別(兩個以上的值) # 由以下例子說明: 構建一個系統去除圖片的雜訊 # 注意: 此分類器的輸出是多個標籤(一個pixel 一個label, 像素強度範圍 0~255) # 首先, 先把乾淨的圖片加入雜訊並創建訓練集和測試集 rnd = np.RandomState(42) noise_train = rnd.randint(0, 100, (len(X_train)), 784) noise_test = rnd.randint(0, 100, (len(X_test)), 784) X_train_mod = X_train + noise_train X_test_mod = X_test + noise_test y_train_mod = X_train y_test_mod = X_test
def fit(self, X_train, y_train):
self.n_classes = len(np.unique(y_train))
self.estimators_levels = []
klass = self.base_estimator.__class__
predictions_levels = []
self.classes = np.unique(y_train)
# first level
estimators = [klass(**params) for params in self.params_list]
self.estimators_levels.append(estimators)
predictions = []
for estimator in estimators:
estimator.fit(X_train, y_train)
if self.k_fold > 1: # use cv
predict_ = cvp(estimator,
X_train,
y_train,
cv=self.k_fold,
n_jobs=-1)
else: # use oob
predict_ = estimator.oob_decision_function_
# fill default value if meet nan
inds = np.where(np.isnan(predict_))
predict_[inds] = 1. / self.n_classes
predictions.append(predict_)
attr_to_next_level = np.hstack(predictions)
y_pre = self.classes.take(np.argmax(np.array(predictions).mean(axis=0),
axis=1),
axis=0)
self.max_accuracy = self.evaluate(y_pre, y_train)
# cascade step
while True:
print('level {}, CV accuracy: {}'.format(
len(self.estimators_levels), self.max_accuracy))
estimators = [klass(**params) for params in self.params_list]
self.estimators_levels.append(estimators)
predictions = []
X_train_step = np.hstack((attr_to_next_level, X_train))
for estimator in estimators:
estimator.fit(X_train_step, y_train)
if self.k_fold > 1: # use cv
predict_ = cvp(estimator,
X_train_step,
y_train,
cv=self.k_fold,
n_jobs=-1)
else: # use oob
predict_ = estimator.oob_decision_function_
# fill default value if meet nan
inds = np.where(np.isnan(predict_))
predict_[inds] = 1. / self.n_classes
predictions.append(predict_)
attr_to_next_level = np.hstack(predictions)
y_pre = self.classes.take(np.argmax(
np.array(predictions).mean(axis=0), axis=1),
axis=0)
accuracy = self.evaluate(y_pre, y_train)
if accuracy > self.max_accuracy:
self.max_accuracy = accuracy
else:
self.estimators_levels.pop()
break
