def cor_of_features(features, scores):
"""
Paras:
features:
the matrix of feature values, shape of which is (M, N).
--M is the number of samples and N is the number of features(8 for now).
--features[i][j] is the NO.j feature value of NO.i sample.
feature sequence is ['1gram', '2gram', '3gram', '4gram', 'lengthratio', 'lsagrade', 'vecsim', 'fluency'].
scores:
matrix of scores, shape of which is (M, 1).
--M is the number of samples.
returns:
A dict, key of which is feature name and value is pearson correlation value.
"""
cors = {}
i = 0
features_arr = np.asarray(features)
for f in [
'1gram', '2gram', '3gram', '4gram', 'lengthratio', 'lsagrade',
'vec', 'fluency', 'np', 'vp'
]:
cors[f] = round(pearson_cor(scores, features_arr[:, i]), 4)
i += 1
print(cors)
return cors
# selectionKBest.fit(X_rg_scaled, y_rg)
# print(selectionKBest.scores_)
# X_rg_selected = selectionKBest.transform(X_rg_scaled)
# print(X_rg_selected.shape)
rfr, test_scores = random_forest(X_rg_scaled, y_rg, cv=cv)
print(rfr)
print("test scores:", test_scores)
X_train, X_test, y_train, y_test = train_test_split(X_rg_scaled,
y_rg,
test_size=0.2,
random_state=42)
rfr.fit(X_train, y_train)
print(rfr.feature_importances_)
print("number of features:", rfr.n_features_)
print("pearson:", pearson_cor(y_test, rfr.predict(X_test)))
# print("s:", s, "n:", n, "test_scores", test_scores)
# if test_scores[-1] > max_score:
# best_feature_num = n
# max_score = max(max_score, test_scores[-1])
# best_selection = s
# print("best selection:", best_selection)
# print("selected feature number:", best_feature_num, "max test scores:", max_score)
# classfication model
# X_clf, y = extract_data(conn, course="202英语二", features=features3)
# scaler = MinMaxScaler()
# X_clf_scaled = scaler.fit_transform(X_clf)
# y_clf = [str(data) for data in y]
# svc = classification(X_clf_scaled, y_clf, cv=cv)
from feature import extract_features
import numpy as np
import math
from correlation import pearson_cor
feature_list, score_list = extract_features()
new_scores = np.array(score_list) / 2.0
predict_scores = []
for f in feature_list:
# print(f)
length_ratio = f[4] # candidate length / reference length
if length_ratio == 0:
BLEU = 0
else:
BP = 1 if length_ratio > 1 else math.exp(1 - 1 / length_ratio)
BLEU = BP * math.exp(sum(math.log(p) for p in f[:4]) * 0.25) if f[0]*f[1]*f[2]*f[3] != 0 else 0
predict_scores.append(BLEU)
print(new_scores)
print(predict_scores)
print(pearson_cor(new_scores, predict_scores))
y_rg,
ylim=(0.0, 0.8),
cv=cv,
n_jobs=4,
scoring=score_func)
plt.show()
# X_train, X_test, y_train, y_test = train_test_split(X_rg_scaled, y_rg, test_size=0.33, random_state=42)
X_train = X_rg_scaled[100:]
y_train = y_rg[100:]
X_test = X_rg_scaled[:100]
y_test = y_rg[:100]
best_svr.fit(X_train, y_train)
y_predict = best_svr.predict(X_test)
print(pearson_cor(y_test, y_predict))
# conn = pymysql.connect(host="127.0.0.1",
# database='essaydata',
# port=3306,
# user='******',
# password='',
# charset='utf8')
# cur = conn.cursor()
# sql = "SELECT textid FROM features WHERE 1gram=%s AND 2gram=%s AND 3gram=%s AND 4gram=%s"
# sql1 = "SELECT textid, text FROM detection WHERE textid=%s"
# for index in range(len(y_test)):
# if abs(y_test[index] - y_predict[index]) > 0.3:
#
# print("target:", y_test[index], "predict:", y_predict[index])