From 4709691adf5c1873eae668b710c56b0fb5f2add5 Mon Sep 17 00:00:00 2001
From: Alicja Szulecka <73056579+AliSzu@users.noreply.github.com>
Date: Sat, 13 Apr 2024 19:07:21 +0200
Subject: [PATCH] first script

---
 IUM_2.py | 42 ++++++++++++++++++++----------------------
 1 file changed, 20 insertions(+), 22 deletions(-)

diff --git a/IUM_2.py b/IUM_2.py
index 5fa7a25..e2807fb 100644
--- a/IUM_2.py
+++ b/IUM_2.py
@@ -3,38 +3,36 @@ from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import StandardScaler
 
 def split(data):
-    meteorite_train, meteorite_test = train_test_split(data, test_size=0.2, random_state=1)
-    meteorite_train, meteorite_val = train_test_split(meteorite_train, test_size=0.25, random_state=1)
-    return meteorite_train, meteorite_test, meteorite_val
+    forest_train, forest_test = train_test_split(data, test_size=0.2, random_state=1)
+    forest_train, forest_val = train_test_split(forest_train, test_size=0.25, random_state=1)
+    return forest_train, forest_test, forest_val
 
 def normalization(data):
     scaler = StandardScaler()
-    data['mass'] = scaler.fit_transform(data[['mass']])
+    columns_to_normalize = data.columns[~data.columns.str.startswith('Soil_Type')]
+    columns_to_normalize = columns_to_normalize.to_list()
+    columns_to_normalize.remove('Cover_Type')
+    data[columns_to_normalize] = scaler.fit_transform(data[columns_to_normalize])
     return data
 
 def preprocessing(data):
-    data = data.dropna(subset=['reclat'])
-
-    incorrect_years_index  = data.loc[(data['year'] > 2016) | (data['year'] < 860)].index
-    incorrect_location_index  = data.loc[(data['reclat'] == 0) & (data['reclong'] == 0)].index
-
-    data.drop(incorrect_years_index.union(incorrect_location_index), inplace=True)
-    data.loc[(data['mass'].isnull()) & (data['name'].str.startswith('Österplana')), 'mass'] = 0
+    #shuffle
+    data = data.sample(frac = 1)
     return data
 
-data = pd.read_csv("meteorite-landings.csv")
-meteorite_train, meteorite_test, meteorite_val = split(data)
+data = pd.read_csv("covtype.csv")
+forest_train, forest_test, forest_val = split(data)
 
-meteorite_train = normalization(meteorite_train)
-meteorite_test = normalization(meteorite_test)
-meteorite_val = normalization(meteorite_val)
+forest_train = preprocessing(forest_train)
+forest_test = preprocessing(forest_test)
+forest_val = preprocessing(forest_val)
 
-meteorite_train = normalization(meteorite_train)
-meteorite_test = normalization(meteorite_test)
-meteorite_val = normalization(meteorite_val)
+forest_train = normalization(forest_train)
+forest_test = normalization(forest_test)
+forest_val = normalization(forest_val)
 
-meteorite_train.to_csv('meteorite_train.csv', encoding='utf-8')
-meteorite_test.to_csv('meteorite_test.csv', encoding='utf-8')
-meteorite_val.to_csv('meteorite_val.csv', encoding='utf-8')
+forest_train.to_csv('forest_train.csv', encoding='utf-8', index=False)
+forest_test.to_csv('forest_test.csv', encoding='utf-8', index=False)
+forest_val.to_csv('forest_val.csv', encoding='utf-8', index=False)