{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/train.csv')\ntrain","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['sex'] = train['sex'].fillna('unknown')\ntrain['age_approx'] = train['age_approx'].fillna(train['age_approx'].median())\ntrain['anatom_site_general_challenge'] = train['anatom_site_general_challenge'].fillna('unknown')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test['anatom_site_general_challenge'] = test['anatom_site_general_challenge'].fillna('unknown')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.drop(['diagnosis', 'benign_malignant'],axis=True,inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\n\nle = LabelEncoder()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['image_name'] = le.fit_transform(train['image_name'])\ntrain['patient_id'] = le.fit_transform(train['patient_id'])\ntrain['sex'] = le.fit_transform(train['sex'])\ntrain['anatom_site_general_challenge'] = le.fit_transform(train['anatom_site_general_challenge'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train.drop(['target'], axis=1)\ny = train.target","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from xgboost import XGBClassifier\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.ensemble import RandomForestClassifier,BaggingClassifier,AdaBoostClassifier,GradientBoostingClassifier\nfrom sklearn.ensemble import VotingClassifier\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import lightgbm as lgb","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from lightgbm import LGBMClassifier","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = LGBMClassifier()\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X,y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"z = test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"z","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"z['image_name'] = le.fit_transform(z['image_name'])\nz['patient_id'] = le.fit_transform(z['patient_id'])\nz['sex'] = le.fit_transform(z['sex'])\nz['anatom_site_general_challenge'] = le.fit_transform(z['anatom_site_general_challenge'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"z","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"z","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"target = model.predict(z)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x = pd.DataFrame(target,columns=['target'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"q = pd.read_csv('/kaggle/input/siim-isic-melanoma-classification/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = q.join(x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = y.drop(['patient_id','sex','age_approx','anatom_site_general_challenge'],axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y.to_csv('siim.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}