From 83361bdf43f3ac82c65558565a60a924b9c6b02c Mon Sep 17 00:00:00 2001
From: Karolina Oparczyk <karopa@st.amu.edu.pl>
Date: Mon, 17 May 2021 19:24:30 +0200
Subject: [PATCH] nan error fix v2

---
 get_data.sh       |  2 +-
 neural_network.py | 37 +++++++++++++++++++++++++++++--------
 2 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/get_data.sh b/get_data.sh
index 9bf4dd7..e6d03bf 100644
--- a/get_data.sh
+++ b/get_data.sh
@@ -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
\ No newline at end of file
diff --git a/neural_network.py b/neural_network.py
index 71d2253..5ecd857 100644
--- a/neural_network.py
+++ b/neural_network.py
@@ -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)