def test_oov_emb(self):
"""测试 OOV word embedding"""
w = '，'
comma_res = text2vec.encode(w)
print(w, comma_res)
self.assertEqual(comma_res, 0.0)
w = '特价机票'
r = text2vec.encode(w)
print(w, r)
w = '特价'
r1 = text2vec.encode(w)
print(w, r1)
w = '机票'
r2 = text2vec.encode(w)
print(w, r2)
emb = [r1, r2]
r_average = np.array(emb).sum(axis=0) / 2.0
print('r_average:', r_average)
if str(r) == str(r_average):
print('same')
self.assertTrue(str(r) == str(r_average))
def test_sentence_emb():
char = '你'
result = text2vec.encode(char)
print(char, result)
char = '好'
result = text2vec.encode(char)
print(char, result)
char = '吗'
result = text2vec.encode(char)
print(char, result)
char = '你好'
result = text2vec.encode(char)
print(char, result)
char = '你好吗'
result = text2vec.encode(char)
print(char, result)
import numpy as np
emb = [text2vec.encode('你好'), text2vec.encode('吗')]
average = np.array(emb).sum(axis=0) / 2.0
print('average:', average)
act = text2vec.encode('你好吗')
if str(act) == str(average):
print("same")
else:
print('diff')
def test_oov_emb():
char = '，'
result = text2vec.encode(char)
print(char, result)
char = '特价机票'
result = text2vec.encode(char)
print(char, result)
char = '特价'
result = text2vec.encode(char)
print(char, result)
char = '机票'
result = text2vec.encode(char)
print(char, result)
def test_encode_text(self):
"""测试文本 text encode结果"""
a = '如何更换花呗绑定银行卡'
emb = text2vec.encode(a)
print(a, emb)
self.assertEqual(emb.shape, (200, ))
self.assertTrue(' '.join(["{:.3f}".format(i)
for i in emb[:3]]) == "0.041 -0.126 0.019")
def test_encode_word(self):
"""测试文本 word encode结果"""
word = '银行卡'
emb = text2vec.encode(word)
print(word, emb)
self.assertEqual(emb.shape, (200, ))
self.assertTrue(' '.join(["{:.3f}".format(i)
for i in emb[:3]]) == "0.002 -0.126 0.053")
def test_encode_char(self):
"""测试文本 char encode结果"""
char = '卡'
emb = text2vec.encode(char)
t = type(emb)
print(t)
self.assertTrue(t == np.ndarray)
print(char, emb, emb.shape)
self.assertEqual(emb.shape, (200, ))
print(' '.join(["{:.3f}".format(i) for i in emb[:3]]))
self.assertTrue(' '.join(["{:.3f}".format(i)
for i in emb[:3]]) == "0.068 -0.110 -0.048")
@author:XuMing([email protected]) @description: """ import sys import numpy as np sys.path.append('..') import text2vec text2vec.set_log_level('INFO') if __name__ == '__main__': char = '卡' emb = text2vec.encode(char) print(type(emb), emb.shape) print(char, emb) word = '银行卡' print(word, text2vec.encode(word)) a = '如何更换花呗绑定银行卡' emb = text2vec.encode(a) print(a, emb) b = [ '卡', '银行卡', '如何更换花呗绑定银行卡', '如何更换花呗绑定银行卡,如何更换花呗绑定银行卡。如何更换花呗绑定银行卡？。。。这个，如何更换花呗绑定银行卡！' ] res = []
# -*- coding: utf-8 -*- """ @author:XuMing（[email protected]) @description: """ import text2vec a = '如何更换花呗绑定银行卡' b = '花呗更改绑定银行卡' c = '我什么时候开通了花呗' emb = text2vec.encode(a) print(emb) s = text2vec.score(a, b) print(a, b, s) s = text2vec.score(a, c) print(a, c, s) s = text2vec.score(b, c) print(b, c, s)
def similarProj(request):
final_result = {"fundraisings": [], "rates": [], "points": [], "chart": []}
if request.method == "POST":
try:
# 處理資料
text2vec_df = pd.read_pickle(
"/Users/hw_students/proj02/proj02_data/text2vec_df.pkl")
df = pd.read_pickle("/Users/hw_students/proj02/proj02_data/df.pkl")
# 處理Input
userdata = request.data
print("userdata:")
print(userdata)
unit = np.array(list(userdata[0].values()))
# unit = unit.reshape(1, -1) #全部放到同一個陣列
# 把使用者的文本放入
text2vec_df = text2vec_df.append(
pd.DataFrame(text2vec.encode(unit[5])).T)
# 把使用者的專案放入
print(unit[0])
titles = df.title.tolist() + [unit[0]]
# titles = df.title.tolist() + ["-1"]
cs = cosine_similarity(text2vec_df)
###相似案例
RETURN_NUMBER = 3
similar_project = getSimiliarArticle(
-1, cs, titles) # 分數>0.9 的所有募資案id(type=list)
new = df[df["title"].apply(
lambda x: x in similar_project[:RETURN_NUMBER])]
fundraisings = campaignlist(new)
final_result["fundraisings"] = fundraisings
# print("similar_project")
# print(similar_project)
###取十筆
NUMBER = 10
df_10 = df[df["title"].apply(
lambda x: x in similar_project[:NUMBER])]
ten_proj = []
for i in range(len(df_10)):
one_proj = {}
one_proj["id"] = int(df_10.iloc[i:i + 1, :].id.values[0])
one_proj["title"] = str(df_10.iloc[i:i + 1, :].title.values[0])
one_proj["url"] = str(df_10.iloc[i:i + 1, :].url.values[0])
funding_target = int(df_10.iloc[i:i +
1, :].funding_target.values[0])
now_funding = int(df_10.iloc[i:i + 1, :].now_funding.values[0])
one_proj["amountRaised"] = now_funding
one_proj["amountReached"] = funding_target
one_proj["proportion"] = round(
now_funding / funding_target * 100, 2)
one_proj["status"] = str(df_10.iloc[i:i +
1, :].status.values[0])
ten_proj.append(one_proj)
final_result["rates"] = ten_proj
###處理落點分布
CALCULATE_NUMBER = 15
df_15 = df[df["title"].apply(
lambda x: x in similar_project[:CALCULATE_NUMBER])]
#print(similar_project[:CALCULATE_NUMBER])
points = {}
points["averageTarget"] = funding_target_med(df_15)
points["userTarget"] = unit[2]
points["averageTime"] = days_med(df_15)
points["userTime"] = unit[3]
points["averageFeedback"] = cam_count_med(df_15)
points["userFeedback"] = unit[4]
final_result["points"] = points
###處理圖表
# 找出和輸入金額最接近的十筆募資案
money = int(unit[2]) # 使用者輸入的金額
df3 = pd.DataFrame()
df3 = funding_target_similar(money, df)
# 分割回饋方案
list3 = campaignlist_origin(df3)
# print(list3)
# 相似金額分布
chart = funding_table(list3, df3)
final_result["chart"] = chart
print(final_result)
return JsonResponse(final_result, safe=False)
except ValueError as e:
return Response(e.args[0], status.HTTP_400_BAD_REQUEST)
