s434765/ium_434765
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

nan error fix v2
All checks were successful
s434765-training/pipeline/head This commit looks good
Details

Browse Source
This commit is contained in:
Karolina Oparczyk 2021-05-17 19:24:30 +02:00
parent 9feb02a3b8
commit 83361bdf43
2 changed files with 30 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
get_data.sh
View File

@ -7,6 +7,6 @@ if kaggle datasets download -d sgonkaggle/youtube-trend-with-subscriber && unzip
head -n -1 "USvideos_modified.csv" | shuf > "data_shuf"
head -n 544 "data_shuf" > "data_test"
head -n 1088 "data_shuf" | tail -n 544 > "data_dev"
head -n +1089 "data_shuf" > "data_train"
head -n 5441 "data_shuf" | tail -n 4352 > "data_train"
python3 get_data.py USvideos_modified.csv
fi

37
neural_network.py
View File

@ -1,19 +1,30 @@
import pandas as pd
import numpy as np
from keras import optimizers
from tensorflow import keras
def normalize_data(data):
return (data - np.min(data)) / (np.max(data) - np.min(data))
data = pd.read_csv("data_train", sep=',', error_bad_lines=False).dropna()
X = data.loc[:,data.columns == "2805317"].astype(int)
y = data.loc[:,data.columns == "198909"].astype(int)
min_val_sub = np.min(X)
max_val_sub = np.max(X)
X = (X - min_val_sub) / (max_val_sub - min_val_sub)
print(min_val_sub)
print(max_val_sub)
def NormalizeData(data):
return (data - np.min(data)) / (np.max(data) - np.min(data))
min_val_like = np.min(y)
max_val_like = np.max(y)
y = (y - min_val_like) / (max_val_like - min_val_like)
X = NormalizeData(X)
y = NormalizeData(y)
print(min_val_like)
print(max_val_like)
model = keras.Sequential([
@ -22,7 +33,7 @@ model = keras.Sequential([
keras.layers.Dense(1,activation='relu'),
])
model.compile(loss='mean_absolute_error', optimizer='adam', metrics=['mean_absolute_error'])
model.compile(loss='mean_absolute_error', optimizer="Adam", metrics=['mean_absolute_error'])
model.fit(X, y, epochs=15, validation_split = 0.3)
@ -30,8 +41,18 @@ data = pd.read_csv("data_test", sep=',', error_bad_lines=False).dropna()
X_test = data.loc[:,data.columns == "2805317"].astype(int)
y_test = data.loc[:,data.columns == "198909"].astype(int)
X_test = NormalizeData(X_test)
y_test = NormalizeData(y_test)
min_val_sub = np.min(X_test)
max_val_sub = np.max(X_test)
X_test = (X_test - min_val_sub) / (max_val_sub - min_val_sub)
print(min_val_sub)
print(max_val_sub)
min_val_like = np.min(y_test)
max_val_like = np.max(y_test)
y_test = (y_test - min_val_like) / (max_val_like - min_val_like)
print(min_val_like)
print(max_val_like)
prediction = model.predict(X_test)