Create dataset
This commit is contained in:
parent
55710f0d79
commit
ea3b98f2ef
2
Jenkinsfile
vendored
2
Jenkinsfile
vendored
@ -28,7 +28,7 @@ pipeline {
|
|||||||
withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
|
withEnv(["KAGGLE_USERNAME=${params.KAGGLE_USERNAME}",
|
||||||
"KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
|
"KAGGLE_KEY=${params.KAGGLE_KEY}" ]) {
|
||||||
sh 'kaggle datasets download -d elakiricoder/gender-classification-dataset'
|
sh 'kaggle datasets download -d elakiricoder/gender-classification-dataset'
|
||||||
sh 'unzip -o gender_classification_v7.zip'
|
sh 'unzip -o gender-classification-dataset.zip'
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@ -1,7 +1,7 @@
|
|||||||
import pandas as pd
|
import pandas as pd
|
||||||
from sklearn.preprocessing import MinMaxScaler
|
from sklearn.preprocessing import MinMaxScaler
|
||||||
from sklearn.model_selection import train_test_split
|
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_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)
|
gender_classification_test_final, gender_classification_val_final = train_test_split(gender_classification_test, test_size=0.5, random_state=1)
|
||||||
|
Loading…
Reference in New Issue
Block a user