Spaces:
Sleeping
Sleeping
File size: 7,785 Bytes
5320625 2d20748 5320625 2d20748 5320625 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 |
# %%
import json
import random
from datetime import datetime
import numpy as np
from gensim.models import KeyedVectors
from hints import curiosity, hint
from tracking import (
calculate_moving_average,
calculate_tendency_slope,
)
from sentence_transformers import SentenceTransformer
import warnings
warnings.filterwarnings(action="ignore", category=UserWarning, module="gensim")
class Semantrix:
model_st = SentenceTransformer(
"sentence-transformers/paraphrase-multilingual-mpnet-base-v2"
)
config_file_path = "config/lang.json"
secret_file_path = "config/secret.json"
data_path = "data/"
class DictWrapper:
def __init__(self, data_dict):
self.__dict__.update(data_dict)
def __init__(self, lang=0):
self.lang = lang
self.embeddings_dict = {}
with open(self.config_file_path, "r") as file:
self.Config_full = json.load(file)
with open(self.secret_file_path, "r") as file:
self.secret = json.load(file)
if self.lang == 1:
self.model = KeyedVectors.load("config/w2v_models/eng_w2v_model", mmap="r")
self.Config = self.DictWrapper(self.Config_full["ENG"]["Game"])
self.secret_dict = self.secret["ENG"]
else:
self.model = KeyedVectors.load("config/w2v_models/esp_w2v_model", mmap="r")
self.Config = self.DictWrapper(self.Config_full["SPA"]["Game"])
self.secret_dict = self.secret["SPA"]
with open(self.data_path + "ranking.txt", "w+") as file:
file.write("---------------------------")
def prepare_game(self, difficulty):
self.secret_list = (
self.secret_dict["basic"]
if difficulty <= 2
else self.secret_dict["advanced"]
)
self.secret = self.secret_list.pop(random.randint(0, len(self.secret_list) - 1))
self.secret = self.secret.lower()
self.words = [self.Config.secret_word]
self.scores = [10]
if self.secret not in self.embeddings_dict.keys():
self.embeddings_dict[self.secret] = self.model[self.secret]
self.word_vect = [self.embeddings_dict[self.secret].tolist()]
self.win = False
self.n = 0
self.recent_hint = 0
self.f_dev_avg = 0
self.last_hint = -1
self.difficulty = difficulty
if self.difficulty == 1:
self.n = 3
def preproc_vectors(self, repeated):
ascending_indices = np.argsort(self.scores)
descending_indices = list(ascending_indices[::-1])
ranking_data = []
k = len(self.words) - 1
if repeated != -1:
k = repeated
ranking_data.append(["#" + str(k), self.words[k], self.scores[k]])
ranking_data.append("---------------------------")
for i in descending_indices:
if i == 0:
continue
ranking_data.append(["#" + str(i), self.words[i], self.scores[i]])
with open(self.data_path + "ranking.txt", "w+") as file:
for item in ranking_data:
file.write("%s\n" % item)
def play_game(self, word):
word = word.lower()
if word == "give_up":
text = (
"[lose]"
+ self.Config.Feedback_9
+ self.secret
+ "\n\n"
+ self.Config.Feedback_10
)
return text
if word in self.words:
repeated = self.words.index(word)
else:
repeated = -1
self.words.append(word)
if word not in self.embeddings_dict.keys():
if word not in self.model.key_to_index.keys():
self.words.pop(len(self.words) - 1)
feedback = (
"I don't know that word. Try again."
if self.lang == 1
else "No conozco esa palabra. Inténtalo de nuevo."
)
feedback += (
"[rank]" + open(self.data_path + "ranking.txt", "r").read()
if len(self.words) > 1
else "\n\n"
)
return feedback
embedding = self.model[word]
self.embeddings_dict[word] = embedding
score = round(self.model.similarity(self.secret, word) * 10, 2)
if repeated == -1:
self.word_vect.append(self.embeddings_dict[word].tolist())
self.scores.append(score)
if score <= 2.5:
feedback = self.Config.Feedback_0 + str(score)
elif score > 2.5 and score <= 4.0:
feedback = self.Config.Feedback_1 + str(score)
elif score > 4.0 and score <= 6.0:
feedback = self.Config.Feedback_2 + str(score)
elif score > 6.0 and score <= 7.5:
feedback = self.Config.Feedback_3 + str(score)
elif score > 7.5 and score <= 8.0:
feedback = self.Config.Feedback_4 + str(score)
elif score > 8.0 and score < 10.0:
feedback = self.Config.Feedback_5 + str(score)
else:
self.win = True
feedback = "[win]" + self.Config.Feedback_8
self.words[0] = self.secret
self.words.pop(len(self.words) - 1)
self.word_vect.pop(len(self.word_vect) - 1)
self.scores.pop(len(self.scores) - 1)
if score > self.scores[len(self.scores) - 2] and self.win == False:
feedback += "\n" + self.Config.Feedback_6
elif score < self.scores[len(self.scores) - 2] and self.win == False:
feedback += "\n" + self.Config.Feedback_7
if self.difficulty != 4:
mov_avg = calculate_moving_average(self.scores[1:], 5)
if len(mov_avg) > 1 and self.win == False:
f_dev = calculate_tendency_slope(mov_avg)
f_dev_avg = calculate_moving_average(f_dev, 3)
if f_dev_avg[len(f_dev_avg) - 1] < 0 and self.recent_hint == 0:
i = random.randint(0, len(self.Config.hint_intro) - 1)
feedback += "\n\n[hint]" + self.Config.hint_intro[i]
hint_text, self.n, self.last_hint = hint(
self.secret,
self.n,
self.model_st,
self.last_hint,
self.lang,
(
self.DictWrapper(self.Config_full["ENG"]["Hint"])
if self.lang == 1
else self.DictWrapper(self.Config_full["SPA"]["Hint"])
),
)
feedback += "\n" + hint_text
self.recent_hint = 3
if self.recent_hint != 0:
self.recent_hint -= 1
self.preproc_vectors(repeated)
feedback += "[rank]" + open(self.data_path + "ranking.txt", "r").read()
if self.win:
bold_display = 0
if self.win:
with open(self.data_path + "ranking.txt", "r") as original_file:
file_content = original_file.readlines()
new_file_name = self.secret + "_" + str(datetime.now()) + ".txt"
with open(self.data_path + "plays/" + new_file_name, "w+") as new_file:
new_file.writelines(file_content[2:])
return feedback
def curiosity(self):
feedback = curiosity(
self.secret,
(
self.DictWrapper(self.Config_full["ENG"]["Hint"])
if self.lang == 1
else self.DictWrapper(self.Config_full["SPA"]["Hint"])
),
)
return feedback
|