From ba6c8d5dded4c05172fbc3a10db6fc4d664ce6c8 Mon Sep 17 00:00:00 2001
From: Szymon Bartanowicz <szymon@bartanowicz.pl>
Date: Tue, 14 May 2024 22:39:09 +0200
Subject: [PATCH] fix

---
 model.py   |  2 +-
 script1.sh | 29 ++++++++++++++++++++++++++---
 2 files changed, 27 insertions(+), 4 deletions(-)

diff --git a/model.py b/model.py
index 5f998d1..715453d 100644
--- a/model.py
+++ b/model.py
@@ -8,7 +8,7 @@ from tensorflow.keras.models import Sequential
 from tensorflow.keras.layers import Dense
 import tensorflow as tf
 
-data = pd.read_csv('./openpowerlifting.csv')
+data = pd.read_csv('./data/train.csv')
 
 data = data[['Sex', 'Age', 'BodyweightKg', 'TotalKg']].dropna()
 
diff --git a/script1.sh b/script1.sh
index 1a60f4c..ec007da 100644
--- a/script1.sh
+++ b/script1.sh
@@ -1,11 +1,31 @@
+##!/bin/bash
+#pip install kaggle
+#kaggle datasets download -d open-powerlifting/powerlifting-database
+#unzip -o powerlifting-database.zip
+#DATASET_FILE="openpowerlifting.csv"
+#echo "Obcięte wiersze: ${1}"
+#head -n $1 $DATASET_FILE > cutoff_$DATASET_FILE
+#echo "Podział i wymieszanie"
+#total_lines=$(tail -n +2 cutoff_$DATASET_FILE | wc -l)
+#train_lines=$((total_lines * 90 / 100))
+#dev_lines=$((total_lines * 10 / 100))
+#test_lines=$((total_lines - train_lines - dev_lines))
+#shuf cutoff_$DATASET_FILE -o shuffled.csv
+#head -n $train_lines shuffled.csv > train.csv
+#tail -n $((dev_lines + test_lines)) shuffled.csv | head -n $dev_lines > dev.csv
+#tail -n $test_lines shuffled.csv > test.csv
+#mkdir -p data
+#mv train.csv dev.csv test.csv data/
+
 #!/bin/bash
 pip install kaggle
 kaggle datasets download -d open-powerlifting/powerlifting-database
 unzip -o powerlifting-database.zip
 DATASET_FILE="openpowerlifting.csv"
-echo "Obcięte wiersze: ${1}"
+column_names=$(head -n 1 $DATASET_FILE)
+echo "Truncated rows: ${1}"
 head -n $1 $DATASET_FILE > cutoff_$DATASET_FILE
-echo "Podział i wymieszanie"
+echo "$column_names" > temp && cat cutoff_$DATASET_FILE >> temp && mv temp cutoff_$DATASET_FILE
 total_lines=$(tail -n +2 cutoff_$DATASET_FILE | wc -l)
 train_lines=$((total_lines * 90 / 100))
 dev_lines=$((total_lines * 10 / 100))
@@ -15,4 +35,7 @@ head -n $train_lines shuffled.csv > train.csv
 tail -n $((dev_lines + test_lines)) shuffled.csv | head -n $dev_lines > dev.csv
 tail -n $test_lines shuffled.csv > test.csv
 mkdir -p data
-mv train.csv dev.csv test.csv data/
\ No newline at end of file
+echo "$column_names" | cat - train.csv > temp && mv temp train.csv
+echo "$column_names" | cat - dev.csv > temp && mv temp dev.csv
+echo "$column_names" | cat - test.csv > temp && mv temp test.csv
+mv train.csv dev.csv test.csv data/