From 4192e5f2be27f3a2264674ba0b31a186e151a296 Mon Sep 17 00:00:00 2001 From: BinarySandia04 Date: Thu, 21 May 2026 14:23:16 +0200 Subject: [PATCH] update 2 --- skin_cancer_classification.py | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) diff --git a/skin_cancer_classification.py b/skin_cancer_classification.py index eddbe98..fbf7d51 100644 --- a/skin_cancer_classification.py +++ b/skin_cancer_classification.py @@ -29,6 +29,10 @@ Original file is located at import sys IN_COLAB = 'google.colab' in sys.modules +# f IN_COLAB: +# !pip install pandas numpy matplotlib seaborn pillow scikit-learn tensorflow +# !pip install --upgrade kagglehub[pandas-datasets,hf-datasets] + import kagglehub # Download latest version @@ -180,6 +184,18 @@ df['target'] = df['dx'].map(benign_malignant_dict) # Preview print(df[['dx', 'target']].head()) +from sklearn.model_selection import train_test_split + +train_df, val_df = train_test_split( + df, + test_size=0.2, + stratify=df['target'], + random_state=42 +) + +print("Train size:", len(train_df)) +print("Validation size:", len(val_df)) + # Convert 'target' column to string type for ImageDataGenerator train_df['target'] = train_df['target'].astype(str) val_df['target'] = val_df['target'].astype(str) @@ -198,21 +214,10 @@ plt.show() print(df['target'].value_counts()) -"""### Train / Validation split""" +"""### Train / Validation split -from sklearn.model_selection import train_test_split - -train_df, val_df = train_test_split( - df, - test_size=0.2, - stratify=df['target'], - random_state=42 -) - -print("Train size:", len(train_df)) -print("Validation size:", len(val_df)) - -"""### Class weight (class imbalance)""" +### Class weight (class imbalance) +""" from sklearn.utils.class_weight import compute_class_weight