s460929/paranormal-or-skeptic
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

better code

Browse Source
This commit is contained in:
dylodylo 2020-04-20 16:14:42 +02:00
parent ef7d13af8b
commit 6eb349dc94
1 changed files with 12 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
linear_regression.py
View File

@ -4,7 +4,6 @@ import random
import json
from math import sqrt
# Prints ['Hey', 'you', 'what', 'are', 'you', 'doing', 'here']
def make_dict(path):
dict = {}
with open(path) as in_file:
@ -14,8 +13,8 @@ def make_dict(path):
if not word in dict:
weight = round(random.random()%0.2-0.1,2)
dict[word] = weight
return dict
with open('dict.txt', 'w') as file:
json.dump(dict, file)
def make_posts_list(in_file):
posts = []
@ -35,7 +34,8 @@ def make_exp_list(exp_file):
return exp_list
def train_model(in_path, exp_path):
dict = make_dict(in_path)
with open('dict.txt', 'r') as file:
dict = json.load(file)
posts = make_posts_list(in_path)
exp = make_exp_list(exp_path)
w0 = 0.1
@ -53,22 +53,11 @@ def train_model(in_path, exp_path):
post = (in_line.split('\t')[0])
error_rate = 1
y = int(exp_line)
#loop_counter = 0
#while (error_rate > 0.2 and loop_counter < 10000):
#loop_counter +=1
y_hat = w0
for word in re.findall(r"[\w']+", post):
#dict[word] -= (y_hat - y)*lr
y_hat += dict[word]
loss = (y_hat - y)**2
loss_sum += loss
#error_rate = (y_hat - y)**2
# if loop_counter%1000 == 0:
# print(error_rate)
# loss_cost += error_rate
# if loss_counter%1000==0:
# print(loss_sum/1000)
# loss_sum = 0
#uczenie
delta = (y_hat - y) * lr
@ -86,19 +75,20 @@ def train_model(in_path, exp_path):
last_sum = real_loss
loss_sum = 0
loss_counter = 0
with open('dict.txt', 'w') as file:
dict["w0"] = w0
with open('dict2.txt', 'w') as file:
json.dump(dict, file)
def predict(path):
results = []
with open('dict.txt', 'r') as file:
with open('dict2.txt', 'r') as file:
dict = json.load(file)
with open(path+"/in.tsv") as in_file:
for in_line in in_file:
print("new post" + str(random.randint(0,10)))
post = (in_line.split('\t')[0])
y=0
y=dict["w0"]
for word in re.findall(r"[\w']+", post):
if word in dict:
y += dict[word]
@ -112,8 +102,8 @@ def predict(path):
for i in results:
tsv_writer.writerow(i)
# train_model("train/in.tsv", "train/expected.tsv")
make_dict("train/in.tsv")
train_model("train/in.tsv", "train/expected.tsv")
def check_dev():
with open("dev-0/out.tsv") as out_file, open("dev-0/expected.tsv") as exp_file:
@ -125,4 +115,5 @@ def check_dev():
positive += 1
print(positive/counter)
predict("test-A")
predict("dev-0")
check_dev()