s487179
/
x1
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Create dataset

This commit is contained in:
wojciechbatruszewicz 2023-06-26 19:04:04 +02:00
parent 55710f0d79
commit ea3b98f2ef
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Jenkinsfile vendored
View File

@ -28,7 +28,7 @@ pipeline {
withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
"KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
sh 'kaggle datasets download -d elakiricoder/gender-classification-dataset'
sh 'unzip -o gender_classification_v7.zip'
sh 'unzip -o gender-classification-dataset.zip'
}
}
}

2
createDataset.py
View File

@ -1,7 +1,7 @@
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split
gender_classification = pd.read_csv('gender_classification_v7.csv.csv')
gender_classification = pd.read_csv('gender_classification_v7.csv')
gender_classification_train_final, gender_classification_test = train_test_split(gender_classification, test_size=0.2, random_state=1)
gender_classification_test_final, gender_classification_val_final = train_test_split(gender_classification_test, test_size=0.5, random_state=1)