def draw(clf, ds: DataSet, step):
X = ds.get_X()
y = ds.get_y()
x_min, y_min = np.amin(X, 0)
x_max, y_max = np.amax(X, 0)
xx, yy = np.meshgrid(np.arange(x_min, x_max, step),
np.arange(y_min, y_max, step))
grid = np.c_[xx.ravel(), yy.ravel()]
predict_z = np.array(pm_predict(clf.predict_single, grid,
name='predict')).reshape(xx.shape)
x0, y0 = X[y == -1].T
x1, y1 = X[y == 1].T
X_sup = X[clf.support_indices]
x_sup, y_sup = X_sup.T
def plot(_predict_z):
plt.figure(figsize=(10, 10))
plt.pcolormesh(xx,
yy,
_predict_z,
cmap=plt.get_cmap('seismic'),
shading='auto')
plt.scatter(x0, y0, color='red', s=100)
plt.scatter(x1, y1, color='blue', s=100)
plt.scatter(x_sup, y_sup, color='white', marker='x', s=60)
plt.show()
plot(predict_z)
def choose_best(ds: DataSet):
gs = GridSearchCV(estimator=SMO(),
param_grid=GRID,
cv=4,
scoring='accuracy',
verbose=1,
n_jobs=-1)
gs.fit(ds.get_X(), ds.get_y())
draw_metrics(gs.cv_results_)
print(f'Got best score {gs.best_score_} with params {gs.best_params_}')
return gs.best_params_
def test(ds: DataSet, name):
print("Metric")
train_ds, test_ds = ds.test_train_split(test_size=0.33)
metric_data = {"test": [], "train": []}
def add_metric(ds, clf, ds_name):
metric_data[ds_name].append(accuracy_score(ds.y, clf.predict(ds.X)))
def clbck(clf, step):
add_metric(test_ds, clf, "test")
add_metric(train_ds, clf, "train")
clf = AdaBoost(n_estimator=STEPS, callback=clbck, verbose=True)
clf.fit(train_ds.X, train_ds.y)
metric_plot(metric_data,
x_label='Steps',
x_values=list(range(1, STEPS + 1)),
title=f'Accuracy for {name}',
default_color=True)
def read_dataset(filename) -> DataSet:
data = pd.read_csv(filename)
X = data.values[:, :-1]
tmp_y = data.values[:, -1]
y = np.vectorize(lambda t: 1 if t == 'P' else -1)(tmp_y)
return DataSet(X, y)
import os
import csv
from utils import common
from config import configer
from utils.data_set import DataSet, get_important_subject
def get_run_path():
return os.path.dirname(os.path.realpath(__file__))
if __name__ == "__main__":
configer.load_data(get_run_path())
# 获取专业数据
A = DataSet("2014-2015_计科.csv")
B = DataSet("2016-2017_计科.csv")
C = DataSet("2018-2019_计科.csv")
A.get_special_data()
B.get_special_data()
C.get_special_data()
# 获取课程交集
important = get_important_subject(A.get_column("ZWMC"),
B.get_column("ZWMC"),
C.get_column("ZWMC"))
with open(
os.path.join(configer.get_value("dataset_path"),
"csv/important_sub.txt"), "w+") as w:
w.write(str(important))
print("ok")