Datasets
Models
Downloads: 1
[2b5a37]:
/
lung-cancer-prediction-by-classification.ipynb
1 lines (1 with data), 127.6 kB
{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport os\nimport warnings\nwarnings.filterwarnings(\"ignore\")\nfrom sklearn.ensemble import RandomForestClassifier\nfrom imblearn.ensemble import BalancedRandomForestClassifier\nfrom sklearn import svm\nfrom sklearn.metrics import mean_absolute_error\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.neighbors import KNeighborsClassifier\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n for filename in filenames:\n print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:10.857578Z","iopub.execute_input":"2022-10-29T17:50:10.858142Z","iopub.status.idle":"2022-10-29T17:50:10.869978Z","shell.execute_reply.started":"2022-10-29T17:50:10.858103Z","shell.execute_reply":"2022-10-29T17:50:10.868816Z"},"trusted":true},"execution_count":51,"outputs":[{"name":"stdout","text":"/kaggle/input/lung-cancer-detection/survey lung cancer.csv\n","output_type":"stream"}]},{"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/lung-cancer-detection/survey lung cancer.csv')","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:10.872078Z","iopub.execute_input":"2022-10-29T17:50:10.872417Z","iopub.status.idle":"2022-10-29T17:50:10.886897Z","shell.execute_reply.started":"2022-10-29T17:50:10.872388Z","shell.execute_reply":"2022-10-29T17:50:10.885863Z"},"trusted":true},"execution_count":52,"outputs":[]},{"cell_type":"code","source":"df.shape","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:10.888430Z","iopub.execute_input":"2022-10-29T17:50:10.888939Z","iopub.status.idle":"2022-10-29T17:50:10.895853Z","shell.execute_reply.started":"2022-10-29T17:50:10.888910Z","shell.execute_reply":"2022-10-29T17:50:10.895130Z"},"trusted":true},"execution_count":53,"outputs":[{"execution_count":53,"output_type":"execute_result","data":{"text/plain":"(309, 16)"},"metadata":{}}]},{"cell_type":"code","source":"df.info()","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:10.897526Z","iopub.execute_input":"2022-10-29T17:50:10.897982Z","iopub.status.idle":"2022-10-29T17:50:10.920007Z","shell.execute_reply.started":"2022-10-29T17:50:10.897953Z","shell.execute_reply":"2022-10-29T17:50:10.918724Z"},"trusted":true},"execution_count":54,"outputs":[{"name":"stdout","text":"<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 309 entries, 0 to 308\nData columns (total 16 columns):\n # Column Non-Null Count Dtype \n--- ------ -------------- ----- \n 0 GENDER 309 non-null object\n 1 AGE 309 non-null int64 \n 2 SMOKING 309 non-null int64 \n 3 YELLOW_FINGERS 309 non-null int64 \n 4 ANXIETY 309 non-null int64 \n 5 PEER_PRESSURE 309 non-null int64 \n 6 CHRONIC DISEASE 309 non-null int64 \n 7 FATIGUE 309 non-null int64 \n 8 ALLERGY 309 non-null int64 \n 9 WHEEZING 309 non-null int64 \n 10 ALCOHOL CONSUMING 309 non-null int64 \n 11 COUGHING 309 non-null int64 \n 12 SHORTNESS OF BREATH 309 non-null int64 \n 13 SWALLOWING DIFFICULTY 309 non-null int64 \n 14 CHEST PAIN 309 non-null int64 \n 15 LUNG_CANCER 309 non-null object\ndtypes: int64(14), object(2)\nmemory usage: 38.8+ KB\n","output_type":"stream"}]},{"cell_type":"code","source":"df.describe()","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:10.921219Z","iopub.execute_input":"2022-10-29T17:50:10.921807Z","iopub.status.idle":"2022-10-29T17:50:10.981063Z","shell.execute_reply.started":"2022-10-29T17:50:10.921774Z","shell.execute_reply":"2022-10-29T17:50:10.979940Z"},"trusted":true},"execution_count":55,"outputs":[{"execution_count":55,"output_type":"execute_result","data":{"text/plain":" AGE SMOKING YELLOW_FINGERS ANXIETY PEER_PRESSURE \\\ncount 309.000000 309.000000 309.000000 309.000000 309.000000 \nmean 62.673139 1.563107 1.569579 1.498382 1.501618 \nstd 8.210301 0.496806 0.495938 0.500808 0.500808 \nmin 21.000000 1.000000 1.000000 1.000000 1.000000 \n25% 57.000000 1.000000 1.000000 1.000000 1.000000 \n50% 62.000000 2.000000 2.000000 1.000000 2.000000 \n75% 69.000000 2.000000 2.000000 2.000000 2.000000 \nmax 87.000000 2.000000 2.000000 2.000000 2.000000 \n\n CHRONIC DISEASE FATIGUE ALLERGY WHEEZING ALCOHOL CONSUMING \\\ncount 309.000000 309.000000 309.000000 309.000000 309.000000 \nmean 1.504854 1.673139 1.556634 1.556634 1.556634 \nstd 0.500787 0.469827 0.497588 0.497588 0.497588 \nmin 1.000000 1.000000 1.000000 1.000000 1.000000 \n25% 1.000000 1.000000 1.000000 1.000000 1.000000 \n50% 2.000000 2.000000 2.000000 2.000000 2.000000 \n75% 2.000000 2.000000 2.000000 2.000000 2.000000 \nmax 2.000000 2.000000 2.000000 2.000000 2.000000 \n\n COUGHING SHORTNESS OF BREATH SWALLOWING DIFFICULTY CHEST PAIN \ncount 309.000000 309.000000 309.000000 309.000000 \nmean 1.579288 1.640777 1.469256 1.556634 \nstd 0.494474 0.480551 0.499863 0.497588 \nmin 1.000000 1.000000 1.000000 1.000000 \n25% 1.000000 1.000000 1.000000 1.000000 \n50% 2.000000 2.000000 1.000000 2.000000 \n75% 2.000000 2.000000 2.000000 2.000000 \nmax 2.000000 2.000000 2.000000 2.000000 ","text/html":"<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>AGE</th>\n <th>SMOKING</th>\n <th>YELLOW_FINGERS</th>\n <th>ANXIETY</th>\n <th>PEER_PRESSURE</th>\n <th>CHRONIC DISEASE</th>\n <th>FATIGUE</th>\n <th>ALLERGY</th>\n <th>WHEEZING</th>\n <th>ALCOHOL CONSUMING</th>\n <th>COUGHING</th>\n <th>SHORTNESS OF BREATH</th>\n <th>SWALLOWING DIFFICULTY</th>\n <th>CHEST PAIN</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>count</th>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n <td>309.000000</td>\n </tr>\n <tr>\n <th>mean</th>\n <td>62.673139</td>\n <td>1.563107</td>\n <td>1.569579</td>\n <td>1.498382</td>\n <td>1.501618</td>\n <td>1.504854</td>\n <td>1.673139</td>\n <td>1.556634</td>\n <td>1.556634</td>\n <td>1.556634</td>\n <td>1.579288</td>\n <td>1.640777</td>\n <td>1.469256</td>\n <td>1.556634</td>\n </tr>\n <tr>\n <th>std</th>\n <td>8.210301</td>\n <td>0.496806</td>\n <td>0.495938</td>\n <td>0.500808</td>\n <td>0.500808</td>\n <td>0.500787</td>\n <td>0.469827</td>\n <td>0.497588</td>\n <td>0.497588</td>\n <td>0.497588</td>\n <td>0.494474</td>\n <td>0.480551</td>\n <td>0.499863</td>\n <td>0.497588</td>\n </tr>\n <tr>\n <th>min</th>\n <td>21.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n </tr>\n <tr>\n <th>25%</th>\n <td>57.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n <td>1.000000</td>\n </tr>\n <tr>\n <th>50%</th>\n <td>62.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>1.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>1.000000</td>\n <td>2.000000</td>\n </tr>\n <tr>\n <th>75%</th>\n <td>69.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n </tr>\n <tr>\n <th>max</th>\n <td>87.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n <td>2.000000</td>\n </tr>\n </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df.columns","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:10.982821Z","iopub.execute_input":"2022-10-29T17:50:10.983537Z","iopub.status.idle":"2022-10-29T17:50:10.990301Z","shell.execute_reply.started":"2022-10-29T17:50:10.983501Z","shell.execute_reply":"2022-10-29T17:50:10.989163Z"},"trusted":true},"execution_count":56,"outputs":[{"execution_count":56,"output_type":"execute_result","data":{"text/plain":"Index(['GENDER', 'AGE', 'SMOKING', 'YELLOW_FINGERS', 'ANXIETY',\n 'PEER_PRESSURE', 'CHRONIC DISEASE', 'FATIGUE ', 'ALLERGY ', 'WHEEZING',\n 'ALCOHOL CONSUMING', 'COUGHING', 'SHORTNESS OF BREATH',\n 'SWALLOWING DIFFICULTY', 'CHEST PAIN', 'LUNG_CANCER'],\n dtype='object')"},"metadata":{}}]},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:10.992648Z","iopub.execute_input":"2022-10-29T17:50:10.993132Z","iopub.status.idle":"2022-10-29T17:50:11.016922Z","shell.execute_reply.started":"2022-10-29T17:50:10.993102Z","shell.execute_reply":"2022-10-29T17:50:11.015871Z"},"trusted":true},"execution_count":57,"outputs":[{"execution_count":57,"output_type":"execute_result","data":{"text/plain":" GENDER AGE SMOKING YELLOW_FINGERS ANXIETY PEER_PRESSURE \\\n0 M 69 1 2 2 1 \n1 M 74 2 1 1 1 \n2 F 59 1 1 1 2 \n3 M 63 2 2 2 1 \n4 F 63 1 2 1 1 \n\n CHRONIC DISEASE FATIGUE ALLERGY WHEEZING ALCOHOL CONSUMING COUGHING \\\n0 1 2 1 2 2 2 \n1 2 2 2 1 1 1 \n2 1 2 1 2 1 2 \n3 1 1 1 1 2 1 \n4 1 1 1 2 1 2 \n\n SHORTNESS OF BREATH SWALLOWING DIFFICULTY CHEST PAIN LUNG_CANCER \n0 2 2 2 YES \n1 2 2 2 YES \n2 2 1 2 NO \n3 1 2 2 NO \n4 2 1 1 NO ","text/html":"<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>GENDER</th>\n <th>AGE</th>\n <th>SMOKING</th>\n <th>YELLOW_FINGERS</th>\n <th>ANXIETY</th>\n <th>PEER_PRESSURE</th>\n <th>CHRONIC DISEASE</th>\n <th>FATIGUE</th>\n <th>ALLERGY</th>\n <th>WHEEZING</th>\n <th>ALCOHOL CONSUMING</th>\n <th>COUGHING</th>\n <th>SHORTNESS OF BREATH</th>\n <th>SWALLOWING DIFFICULTY</th>\n <th>CHEST PAIN</th>\n <th>LUNG_CANCER</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>M</td>\n <td>69</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>YES</td>\n </tr>\n <tr>\n <th>1</th>\n <td>M</td>\n <td>74</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>YES</td>\n </tr>\n <tr>\n <th>2</th>\n <td>F</td>\n <td>59</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>NO</td>\n </tr>\n <tr>\n <th>3</th>\n <td>M</td>\n <td>63</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>NO</td>\n </tr>\n <tr>\n <th>4</th>\n <td>F</td>\n <td>63</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>NO</td>\n </tr>\n </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df['LUNG_CANCER']=df['LUNG_CANCER'].map({'YES':2,'NO':1})","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.018847Z","iopub.execute_input":"2022-10-29T17:50:11.019667Z","iopub.status.idle":"2022-10-29T17:50:11.032142Z","shell.execute_reply.started":"2022-10-29T17:50:11.019600Z","shell.execute_reply":"2022-10-29T17:50:11.031173Z"},"trusted":true},"execution_count":58,"outputs":[]},{"cell_type":"code","source":"df['GENDER']=df['GENDER'].map({'M':1,'F':2})","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.033666Z","iopub.execute_input":"2022-10-29T17:50:11.034445Z","iopub.status.idle":"2022-10-29T17:50:11.048490Z","shell.execute_reply.started":"2022-10-29T17:50:11.034409Z","shell.execute_reply":"2022-10-29T17:50:11.047555Z"},"trusted":true},"execution_count":59,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.049530Z","iopub.execute_input":"2022-10-29T17:50:11.050332Z","iopub.status.idle":"2022-10-29T17:50:11.074210Z","shell.execute_reply.started":"2022-10-29T17:50:11.050299Z","shell.execute_reply":"2022-10-29T17:50:11.073325Z"},"trusted":true},"execution_count":60,"outputs":[{"execution_count":60,"output_type":"execute_result","data":{"text/plain":" GENDER AGE SMOKING YELLOW_FINGERS ANXIETY PEER_PRESSURE \\\n0 1 69 1 2 2 1 \n1 1 74 2 1 1 1 \n2 2 59 1 1 1 2 \n3 1 63 2 2 2 1 \n4 2 63 1 2 1 1 \n\n CHRONIC DISEASE FATIGUE ALLERGY WHEEZING ALCOHOL CONSUMING COUGHING \\\n0 1 2 1 2 2 2 \n1 2 2 2 1 1 1 \n2 1 2 1 2 1 2 \n3 1 1 1 1 2 1 \n4 1 1 1 2 1 2 \n\n SHORTNESS OF BREATH SWALLOWING DIFFICULTY CHEST PAIN LUNG_CANCER \n0 2 2 2 2 \n1 2 2 2 2 \n2 2 1 2 1 \n3 1 2 2 1 \n4 2 1 1 1 ","text/html":"<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>GENDER</th>\n <th>AGE</th>\n <th>SMOKING</th>\n <th>YELLOW_FINGERS</th>\n <th>ANXIETY</th>\n <th>PEER_PRESSURE</th>\n <th>CHRONIC DISEASE</th>\n <th>FATIGUE</th>\n <th>ALLERGY</th>\n <th>WHEEZING</th>\n <th>ALCOHOL CONSUMING</th>\n <th>COUGHING</th>\n <th>SHORTNESS OF BREATH</th>\n <th>SWALLOWING DIFFICULTY</th>\n <th>CHEST PAIN</th>\n <th>LUNG_CANCER</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>1</td>\n <td>69</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>1</th>\n <td>1</td>\n <td>74</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>2</th>\n <td>2</td>\n <td>59</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n </tr>\n <tr>\n <th>3</th>\n <td>1</td>\n <td>63</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n </tr>\n <tr>\n <th>4</th>\n <td>2</td>\n <td>63</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n </tr>\n </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df[df.duplicated()]","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.075323Z","iopub.execute_input":"2022-10-29T17:50:11.076207Z","iopub.status.idle":"2022-10-29T17:50:11.106695Z","shell.execute_reply.started":"2022-10-29T17:50:11.076173Z","shell.execute_reply":"2022-10-29T17:50:11.105516Z"},"trusted":true},"execution_count":61,"outputs":[{"execution_count":61,"output_type":"execute_result","data":{"text/plain":" GENDER AGE SMOKING YELLOW_FINGERS ANXIETY PEER_PRESSURE \\\n99 1 56 2 1 1 1 \n100 1 58 2 1 1 1 \n117 2 51 2 2 2 2 \n199 2 55 2 1 1 2 \n212 1 58 2 1 1 1 \n223 1 63 2 2 2 1 \n256 1 60 2 1 1 1 \n275 1 64 2 2 2 2 \n284 1 58 2 2 2 2 \n285 2 58 2 2 2 2 \n286 2 63 1 1 1 1 \n287 2 51 2 2 2 2 \n288 2 61 1 2 2 2 \n289 2 61 2 1 1 1 \n290 1 76 2 1 1 1 \n291 1 71 2 2 2 1 \n292 1 69 1 1 2 1 \n293 2 56 2 2 2 1 \n294 1 67 1 1 1 2 \n295 2 54 2 2 2 1 \n296 1 63 1 2 1 1 \n297 2 47 2 2 1 2 \n298 1 62 2 1 2 1 \n299 1 65 2 2 2 2 \n300 2 63 2 2 2 2 \n301 1 64 1 2 2 2 \n302 2 65 2 2 2 2 \n303 1 51 1 2 1 1 \n304 2 56 1 1 1 2 \n305 1 70 2 1 1 1 \n306 1 58 2 1 1 1 \n307 1 67 2 1 2 1 \n308 1 62 1 1 1 2 \n\n CHRONIC DISEASE FATIGUE ALLERGY WHEEZING ALCOHOL CONSUMING \\\n99 1 2 2 2 2 \n100 1 1 2 2 2 \n117 1 2 2 1 1 \n199 2 2 2 2 2 \n212 1 2 2 2 2 \n223 2 2 2 2 1 \n256 1 2 2 2 2 \n275 2 1 1 1 2 \n284 2 1 1 1 2 \n285 1 2 1 1 1 \n286 2 2 1 1 1 \n287 1 2 1 1 1 \n288 1 1 2 2 1 \n289 2 2 2 1 1 \n290 1 2 2 2 2 \n291 2 1 2 2 2 \n292 1 2 1 2 2 \n293 1 2 2 1 1 \n294 1 2 1 2 1 \n295 2 1 1 2 2 \n296 1 2 1 2 2 \n297 2 2 2 2 1 \n298 1 2 1 2 2 \n299 1 2 2 1 1 \n300 2 2 2 2 1 \n301 1 1 2 1 2 \n302 1 2 1 2 1 \n303 2 2 2 2 2 \n304 2 2 1 1 2 \n305 1 2 2 2 2 \n306 1 1 2 2 2 \n307 1 2 2 1 2 \n308 1 2 2 2 2 \n\n COUGHING SHORTNESS OF BREATH SWALLOWING DIFFICULTY CHEST PAIN \\\n99 2 2 1 2 \n100 2 1 1 1 \n117 1 2 2 1 \n199 1 1 2 2 \n212 2 2 1 2 \n223 1 2 1 1 \n256 2 2 1 2 \n275 1 1 2 2 \n284 1 1 2 2 \n285 2 2 2 1 \n286 1 2 1 1 \n287 1 2 2 1 \n288 2 1 2 1 \n289 1 2 1 1 \n290 2 2 1 2 \n291 2 1 2 2 \n292 2 2 2 1 \n293 1 2 1 2 \n294 2 2 1 2 \n295 1 2 2 2 \n296 2 2 1 1 \n297 2 2 1 1 \n298 2 2 1 2 \n299 1 2 2 1 \n300 2 2 2 2 \n301 1 1 2 2 \n302 2 2 2 1 \n303 2 2 1 2 \n304 2 2 2 1 \n305 2 2 1 2 \n306 2 1 1 2 \n307 2 2 1 2 \n308 1 1 2 1 \n\n LUNG_CANCER \n99 2 \n100 2 \n117 2 \n199 2 \n212 2 \n223 2 \n256 2 \n275 2 \n284 2 \n285 2 \n286 1 \n287 2 \n288 2 \n289 2 \n290 2 \n291 2 \n292 2 \n293 2 \n294 2 \n295 2 \n296 2 \n297 2 \n298 2 \n299 2 \n300 2 \n301 2 \n302 2 \n303 2 \n304 2 \n305 2 \n306 2 \n307 2 \n308 2 ","text/html":"<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>GENDER</th>\n <th>AGE</th>\n <th>SMOKING</th>\n <th>YELLOW_FINGERS</th>\n <th>ANXIETY</th>\n <th>PEER_PRESSURE</th>\n <th>CHRONIC DISEASE</th>\n <th>FATIGUE</th>\n <th>ALLERGY</th>\n <th>WHEEZING</th>\n <th>ALCOHOL CONSUMING</th>\n <th>COUGHING</th>\n <th>SHORTNESS OF BREATH</th>\n <th>SWALLOWING DIFFICULTY</th>\n <th>CHEST PAIN</th>\n <th>LUNG_CANCER</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>99</th>\n <td>1</td>\n <td>56</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>100</th>\n <td>1</td>\n <td>58</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>117</th>\n <td>2</td>\n <td>51</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>199</th>\n <td>2</td>\n <td>55</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>212</th>\n <td>1</td>\n <td>58</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>223</th>\n <td>1</td>\n <td>63</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>256</th>\n <td>1</td>\n <td>60</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>275</th>\n <td>1</td>\n <td>64</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>284</th>\n <td>1</td>\n <td>58</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>285</th>\n <td>2</td>\n <td>58</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>286</th>\n <td>2</td>\n <td>63</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n </tr>\n <tr>\n <th>287</th>\n <td>2</td>\n <td>51</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>288</th>\n <td>2</td>\n <td>61</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>289</th>\n <td>2</td>\n <td>61</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>290</th>\n <td>1</td>\n <td>76</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>291</th>\n <td>1</td>\n <td>71</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>292</th>\n <td>1</td>\n <td>69</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>293</th>\n <td>2</td>\n <td>56</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>294</th>\n <td>1</td>\n <td>67</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>295</th>\n <td>2</td>\n <td>54</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>296</th>\n <td>1</td>\n <td>63</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>297</th>\n <td>2</td>\n <td>47</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>298</th>\n <td>1</td>\n <td>62</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>299</th>\n <td>1</td>\n <td>65</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>300</th>\n <td>2</td>\n <td>63</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>301</th>\n <td>1</td>\n <td>64</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>302</th>\n <td>2</td>\n <td>65</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>303</th>\n <td>1</td>\n <td>51</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>304</th>\n <td>2</td>\n <td>56</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>305</th>\n <td>1</td>\n <td>70</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>306</th>\n <td>1</td>\n <td>58</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>307</th>\n <td>1</td>\n <td>67</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>308</th>\n <td>1</td>\n <td>62</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n </tr>\n </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"df.drop_duplicates()","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.108028Z","iopub.execute_input":"2022-10-29T17:50:11.108362Z","iopub.status.idle":"2022-10-29T17:50:11.131467Z","shell.execute_reply.started":"2022-10-29T17:50:11.108333Z","shell.execute_reply":"2022-10-29T17:50:11.130222Z"},"trusted":true},"execution_count":62,"outputs":[{"execution_count":62,"output_type":"execute_result","data":{"text/plain":" GENDER AGE SMOKING YELLOW_FINGERS ANXIETY PEER_PRESSURE \\\n0 1 69 1 2 2 1 \n1 1 74 2 1 1 1 \n2 2 59 1 1 1 2 \n3 1 63 2 2 2 1 \n4 2 63 1 2 1 1 \n.. ... ... ... ... ... ... \n279 2 59 1 2 2 2 \n280 2 59 2 1 1 1 \n281 1 55 2 1 1 1 \n282 1 46 1 2 2 1 \n283 1 60 1 2 2 1 \n\n CHRONIC DISEASE FATIGUE ALLERGY WHEEZING ALCOHOL CONSUMING \\\n0 1 2 1 2 2 \n1 2 2 2 1 1 \n2 1 2 1 2 1 \n3 1 1 1 1 2 \n4 1 1 1 2 1 \n.. ... ... ... ... ... \n279 1 1 2 2 1 \n280 2 2 2 1 1 \n281 1 2 2 1 1 \n282 1 1 1 1 1 \n283 1 2 1 2 2 \n\n COUGHING SHORTNESS OF BREATH SWALLOWING DIFFICULTY CHEST PAIN \\\n0 2 2 2 2 \n1 1 2 2 2 \n2 2 2 1 2 \n3 1 1 2 2 \n4 2 2 1 1 \n.. ... ... ... ... \n279 2 1 2 1 \n280 1 2 1 1 \n281 1 2 1 2 \n282 1 1 2 2 \n283 2 2 2 2 \n\n LUNG_CANCER \n0 2 \n1 2 \n2 1 \n3 1 \n4 1 \n.. ... \n279 2 \n280 1 \n281 1 \n282 1 \n283 2 \n\n[276 rows x 16 columns]","text/html":"<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>GENDER</th>\n <th>AGE</th>\n <th>SMOKING</th>\n <th>YELLOW_FINGERS</th>\n <th>ANXIETY</th>\n <th>PEER_PRESSURE</th>\n <th>CHRONIC DISEASE</th>\n <th>FATIGUE</th>\n <th>ALLERGY</th>\n <th>WHEEZING</th>\n <th>ALCOHOL CONSUMING</th>\n <th>COUGHING</th>\n <th>SHORTNESS OF BREATH</th>\n <th>SWALLOWING DIFFICULTY</th>\n <th>CHEST PAIN</th>\n <th>LUNG_CANCER</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>1</td>\n <td>69</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>1</th>\n <td>1</td>\n <td>74</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n <tr>\n <th>2</th>\n <td>2</td>\n <td>59</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n </tr>\n <tr>\n <th>3</th>\n <td>1</td>\n <td>63</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n </tr>\n <tr>\n <th>4</th>\n <td>2</td>\n <td>63</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n </tr>\n <tr>\n <th>...</th>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n </tr>\n <tr>\n <th>279</th>\n <td>2</td>\n <td>59</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n </tr>\n <tr>\n <th>280</th>\n <td>2</td>\n <td>59</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n </tr>\n <tr>\n <th>281</th>\n <td>1</td>\n <td>55</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n </tr>\n <tr>\n <th>282</th>\n <td>1</td>\n <td>46</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n </tr>\n <tr>\n <th>283</th>\n <td>1</td>\n <td>60</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>1</td>\n <td>1</td>\n <td>2</td>\n <td>1</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n <td>2</td>\n </tr>\n </tbody>\n</table>\n<p>276 rows × 16 columns</p>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"X = df.iloc[:,:-1]\ny = df['LUNG_CANCER'] ","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.133018Z","iopub.execute_input":"2022-10-29T17:50:11.133419Z","iopub.status.idle":"2022-10-29T17:50:11.143426Z","shell.execute_reply.started":"2022-10-29T17:50:11.133388Z","shell.execute_reply":"2022-10-29T17:50:11.142485Z"},"trusted":true},"execution_count":63,"outputs":[]},{"cell_type":"code","source":"X.shape","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.144947Z","iopub.execute_input":"2022-10-29T17:50:11.145544Z","iopub.status.idle":"2022-10-29T17:50:11.157397Z","shell.execute_reply.started":"2022-10-29T17:50:11.145500Z","shell.execute_reply":"2022-10-29T17:50:11.156570Z"},"trusted":true},"execution_count":64,"outputs":[{"execution_count":64,"output_type":"execute_result","data":{"text/plain":"(309, 15)"},"metadata":{}}]},{"cell_type":"code","source":"y.shape","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.161230Z","iopub.execute_input":"2022-10-29T17:50:11.162394Z","iopub.status.idle":"2022-10-29T17:50:11.171335Z","shell.execute_reply.started":"2022-10-29T17:50:11.162357Z","shell.execute_reply":"2022-10-29T17:50:11.170322Z"},"trusted":true},"execution_count":65,"outputs":[{"execution_count":65,"output_type":"execute_result","data":{"text/plain":"(309,)"},"metadata":{}}]},{"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(X, y, random_state = 42, test_size = 0.2, stratify = y)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.172517Z","iopub.execute_input":"2022-10-29T17:50:11.173201Z","iopub.status.idle":"2022-10-29T17:50:11.186103Z","shell.execute_reply.started":"2022-10-29T17:50:11.173167Z","shell.execute_reply":"2022-10-29T17:50:11.185302Z"},"trusted":true},"execution_count":66,"outputs":[]},{"cell_type":"code","source":"from sklearn.preprocessing import MinMaxScaler\n\nscale=MinMaxScaler()\nX_train_scaled=pd.DataFrame(scale.fit_transform(X_train),columns=X_train.columns)\nX_train_scaled","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.187104Z","iopub.execute_input":"2022-10-29T17:50:11.187893Z","iopub.status.idle":"2022-10-29T17:50:11.227191Z","shell.execute_reply.started":"2022-10-29T17:50:11.187849Z","shell.execute_reply":"2022-10-29T17:50:11.226002Z"},"trusted":true},"execution_count":67,"outputs":[{"execution_count":67,"output_type":"execute_result","data":{"text/plain":" GENDER AGE SMOKING YELLOW_FINGERS ANXIETY PEER_PRESSURE \\\n0 1.0 0.469388 1.0 1.0 1.0 0.0 \n1 1.0 0.530612 1.0 1.0 0.0 1.0 \n2 1.0 0.714286 1.0 1.0 1.0 0.0 \n3 1.0 0.489796 0.0 0.0 0.0 1.0 \n4 0.0 0.265306 0.0 1.0 0.0 0.0 \n.. ... ... ... ... ... ... \n242 1.0 0.387755 0.0 1.0 1.0 0.0 \n243 0.0 0.367347 1.0 1.0 1.0 0.0 \n244 0.0 0.367347 1.0 0.0 0.0 0.0 \n245 0.0 0.265306 0.0 1.0 0.0 0.0 \n246 1.0 0.428571 1.0 0.0 0.0 0.0 \n\n CHRONIC DISEASE FATIGUE ALLERGY WHEEZING ALCOHOL CONSUMING \\\n0 0.0 1.0 1.0 0.0 1.0 \n1 0.0 1.0 0.0 1.0 1.0 \n2 1.0 0.0 1.0 0.0 1.0 \n3 0.0 0.0 0.0 1.0 1.0 \n4 1.0 1.0 1.0 1.0 1.0 \n.. ... ... ... ... ... \n242 0.0 0.0 0.0 0.0 0.0 \n243 0.0 0.0 0.0 0.0 0.0 \n244 0.0 1.0 1.0 1.0 1.0 \n245 1.0 1.0 1.0 1.0 1.0 \n246 1.0 1.0 1.0 0.0 0.0 \n\n COUGHING SHORTNESS OF BREATH SWALLOWING DIFFICULTY CHEST PAIN \n0 0.0 1.0 1.0 1.0 \n1 1.0 0.0 1.0 1.0 \n2 0.0 0.0 0.0 0.0 \n3 0.0 0.0 1.0 1.0 \n4 1.0 1.0 0.0 1.0 \n.. ... ... ... ... \n242 1.0 0.0 0.0 0.0 \n243 0.0 1.0 1.0 0.0 \n244 1.0 1.0 0.0 1.0 \n245 1.0 1.0 0.0 1.0 \n246 0.0 1.0 0.0 0.0 \n\n[247 rows x 15 columns]","text/html":"<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>GENDER</th>\n <th>AGE</th>\n <th>SMOKING</th>\n <th>YELLOW_FINGERS</th>\n <th>ANXIETY</th>\n <th>PEER_PRESSURE</th>\n <th>CHRONIC DISEASE</th>\n <th>FATIGUE</th>\n <th>ALLERGY</th>\n <th>WHEEZING</th>\n <th>ALCOHOL CONSUMING</th>\n <th>COUGHING</th>\n <th>SHORTNESS OF BREATH</th>\n <th>SWALLOWING DIFFICULTY</th>\n <th>CHEST PAIN</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>1.0</td>\n <td>0.469388</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>1</th>\n <td>1.0</td>\n <td>0.530612</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>2</th>\n <td>1.0</td>\n <td>0.714286</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n </tr>\n <tr>\n <th>3</th>\n <td>1.0</td>\n <td>0.489796</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>4</th>\n <td>0.0</td>\n <td>0.265306</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>...</th>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n </tr>\n <tr>\n <th>242</th>\n <td>1.0</td>\n <td>0.387755</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n </tr>\n <tr>\n <th>243</th>\n <td>0.0</td>\n <td>0.367347</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n </tr>\n <tr>\n <th>244</th>\n <td>0.0</td>\n <td>0.367347</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>245</th>\n <td>0.0</td>\n <td>0.265306</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>246</th>\n <td>1.0</td>\n <td>0.428571</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n </tr>\n </tbody>\n</table>\n<p>247 rows × 15 columns</p>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"X_test_scaled = pd.DataFrame(scale.fit_transform(X_test),columns=X_test.columns)\nX_test_scaled","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.228623Z","iopub.execute_input":"2022-10-29T17:50:11.228966Z","iopub.status.idle":"2022-10-29T17:50:11.267842Z","shell.execute_reply.started":"2022-10-29T17:50:11.228935Z","shell.execute_reply":"2022-10-29T17:50:11.266667Z"},"trusted":true},"execution_count":68,"outputs":[{"execution_count":68,"output_type":"execute_result","data":{"text/plain":" GENDER AGE SMOKING YELLOW_FINGERS ANXIETY PEER_PRESSURE \\\n0 1.0 0.964912 1.0 1.0 1.0 1.0 \n1 0.0 0.614035 1.0 0.0 0.0 0.0 \n2 1.0 0.824561 0.0 0.0 1.0 0.0 \n3 0.0 0.684211 0.0 1.0 1.0 0.0 \n4 1.0 0.736842 0.0 0.0 0.0 0.0 \n.. ... ... ... ... ... ... \n57 0.0 0.456140 0.0 1.0 0.0 1.0 \n58 0.0 0.701754 1.0 1.0 1.0 0.0 \n59 0.0 0.754386 0.0 1.0 1.0 1.0 \n60 1.0 0.771930 1.0 1.0 1.0 1.0 \n61 1.0 0.578947 1.0 1.0 1.0 1.0 \n\n CHRONIC DISEASE FATIGUE ALLERGY WHEEZING ALCOHOL CONSUMING \\\n0 0.0 1.0 1.0 0.0 0.0 \n1 1.0 0.0 1.0 1.0 1.0 \n2 1.0 0.0 1.0 1.0 1.0 \n3 0.0 1.0 0.0 1.0 1.0 \n4 1.0 1.0 0.0 0.0 0.0 \n.. ... ... ... ... ... \n57 1.0 1.0 0.0 1.0 0.0 \n58 0.0 1.0 1.0 0.0 1.0 \n59 0.0 1.0 1.0 0.0 0.0 \n60 0.0 1.0 0.0 1.0 0.0 \n61 1.0 1.0 0.0 0.0 0.0 \n\n COUGHING SHORTNESS OF BREATH SWALLOWING DIFFICULTY CHEST PAIN \n0 0.0 1.0 1.0 1.0 \n1 1.0 1.0 0.0 1.0 \n2 0.0 0.0 1.0 0.0 \n3 1.0 1.0 1.0 1.0 \n4 0.0 1.0 0.0 0.0 \n.. ... ... ... ... \n57 0.0 1.0 1.0 1.0 \n58 0.0 1.0 1.0 1.0 \n59 1.0 0.0 1.0 0.0 \n60 1.0 1.0 1.0 0.0 \n61 0.0 1.0 1.0 0.0 \n\n[62 rows x 15 columns]","text/html":"<div>\n<style scoped>\n .dataframe tbody tr th:only-of-type {\n vertical-align: middle;\n }\n\n .dataframe tbody tr th {\n vertical-align: top;\n }\n\n .dataframe thead th {\n text-align: right;\n }\n</style>\n<table border=\"1\" class=\"dataframe\">\n <thead>\n <tr style=\"text-align: right;\">\n <th></th>\n <th>GENDER</th>\n <th>AGE</th>\n <th>SMOKING</th>\n <th>YELLOW_FINGERS</th>\n <th>ANXIETY</th>\n <th>PEER_PRESSURE</th>\n <th>CHRONIC DISEASE</th>\n <th>FATIGUE</th>\n <th>ALLERGY</th>\n <th>WHEEZING</th>\n <th>ALCOHOL CONSUMING</th>\n <th>COUGHING</th>\n <th>SHORTNESS OF BREATH</th>\n <th>SWALLOWING DIFFICULTY</th>\n <th>CHEST PAIN</th>\n </tr>\n </thead>\n <tbody>\n <tr>\n <th>0</th>\n <td>1.0</td>\n <td>0.964912</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>1</th>\n <td>0.0</td>\n <td>0.614035</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>2</th>\n <td>1.0</td>\n <td>0.824561</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n </tr>\n <tr>\n <th>3</th>\n <td>0.0</td>\n <td>0.684211</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>4</th>\n <td>1.0</td>\n <td>0.736842</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n </tr>\n <tr>\n <th>...</th>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n <td>...</td>\n </tr>\n <tr>\n <th>57</th>\n <td>0.0</td>\n <td>0.456140</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>58</th>\n <td>0.0</td>\n <td>0.701754</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n </tr>\n <tr>\n <th>59</th>\n <td>0.0</td>\n <td>0.754386</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n </tr>\n <tr>\n <th>60</th>\n <td>1.0</td>\n <td>0.771930</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n </tr>\n <tr>\n <th>61</th>\n <td>1.0</td>\n <td>0.578947</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>0.0</td>\n <td>1.0</td>\n <td>1.0</td>\n <td>0.0</td>\n </tr>\n </tbody>\n</table>\n<p>62 rows × 15 columns</p>\n</div>"},"metadata":{}}]},{"cell_type":"markdown","source":"# Random Forest Classifier","metadata":{}},{"cell_type":"code","source":"randforest = RandomForestClassifier() \nrandforest.fit(X_train, y_train)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.269672Z","iopub.execute_input":"2022-10-29T17:50:11.270389Z","iopub.status.idle":"2022-10-29T17:50:11.439364Z","shell.execute_reply.started":"2022-10-29T17:50:11.270338Z","shell.execute_reply":"2022-10-29T17:50:11.438132Z"},"trusted":true},"execution_count":69,"outputs":[{"execution_count":69,"output_type":"execute_result","data":{"text/plain":"RandomForestClassifier()"},"metadata":{}}]},{"cell_type":"code","source":"from sklearn.metrics import mean_absolute_error\n\npredictions_1 = randforest.predict(X_test)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.441087Z","iopub.execute_input":"2022-10-29T17:50:11.441541Z","iopub.status.idle":"2022-10-29T17:50:11.463421Z","shell.execute_reply.started":"2022-10-29T17:50:11.441498Z","shell.execute_reply":"2022-10-29T17:50:11.462216Z"},"trusted":true},"execution_count":70,"outputs":[]},{"cell_type":"code","source":"mae_1 = mean_absolute_error(predictions_1 ,y_test ) \n\nprint(\"Mean Absolute Error with Random Forest classifier:\" , mae_1)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.466076Z","iopub.execute_input":"2022-10-29T17:50:11.467017Z","iopub.status.idle":"2022-10-29T17:50:11.473241Z","shell.execute_reply.started":"2022-10-29T17:50:11.466982Z","shell.execute_reply":"2022-10-29T17:50:11.472403Z"},"trusted":true},"execution_count":71,"outputs":[{"name":"stdout","text":"Mean Absolute Error with Random Forest classifier: 0.0967741935483871\n","output_type":"stream"}]},{"cell_type":"markdown","source":"# Support Vector Machine Classifier","metadata":{}},{"cell_type":"code","source":"svmclass = svm.SVC()\n\n# Fit \nsvmclass.fit(X_train, y_train)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.474189Z","iopub.execute_input":"2022-10-29T17:50:11.474588Z","iopub.status.idle":"2022-10-29T17:50:11.490764Z","shell.execute_reply.started":"2022-10-29T17:50:11.474492Z","shell.execute_reply":"2022-10-29T17:50:11.489478Z"},"trusted":true},"execution_count":72,"outputs":[{"execution_count":72,"output_type":"execute_result","data":{"text/plain":"SVC()"},"metadata":{}}]},{"cell_type":"code","source":"# Make predictions calculate mean absolute error\n\npredictions_2 = svmclass.predict(X_test)\nmae_2 = mean_absolute_error(predictions_2, y_test)\n\nprint(\"Mean Absolute Error with Support Vector Machine: {:,.0f}\".format(mae_2))","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.492219Z","iopub.execute_input":"2022-10-29T17:50:11.492547Z","iopub.status.idle":"2022-10-29T17:50:11.502205Z","shell.execute_reply.started":"2022-10-29T17:50:11.492520Z","shell.execute_reply":"2022-10-29T17:50:11.501080Z"},"trusted":true},"execution_count":73,"outputs":[{"name":"stdout","text":"Mean Absolute Error with Support Vector Machine: 0\n","output_type":"stream"}]},{"cell_type":"markdown","source":"# K-NN","metadata":{}},{"cell_type":"code","source":"knnclass = KNeighborsClassifier(n_neighbors=5)\n\n# Fit \nknnclass.fit(X_train, y_train)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.503509Z","iopub.execute_input":"2022-10-29T17:50:11.504357Z","iopub.status.idle":"2022-10-29T17:50:11.517625Z","shell.execute_reply.started":"2022-10-29T17:50:11.504314Z","shell.execute_reply":"2022-10-29T17:50:11.516228Z"},"trusted":true},"execution_count":74,"outputs":[{"execution_count":74,"output_type":"execute_result","data":{"text/plain":"KNeighborsClassifier()"},"metadata":{}}]},{"cell_type":"code","source":"\npredictions_3 = knnclass.predict(X_test)\nmae_3 = mean_absolute_error(predictions_3, y_test)\n\nprint(\"Mean Absolute Error : {:,.0f}\".format(mae_3))","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.519092Z","iopub.execute_input":"2022-10-29T17:50:11.519420Z","iopub.status.idle":"2022-10-29T17:50:11.532523Z","shell.execute_reply.started":"2022-10-29T17:50:11.519390Z","shell.execute_reply":"2022-10-29T17:50:11.531696Z"},"trusted":true},"execution_count":75,"outputs":[{"name":"stdout","text":"Mean Absolute Error : 0\n","output_type":"stream"}]},{"cell_type":"code","source":"print('Random Forest classifier Predictions - ', predictions_1)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.533947Z","iopub.execute_input":"2022-10-29T17:50:11.534308Z","iopub.status.idle":"2022-10-29T17:50:11.540503Z","shell.execute_reply.started":"2022-10-29T17:50:11.534277Z","shell.execute_reply":"2022-10-29T17:50:11.539524Z"},"trusted":true},"execution_count":76,"outputs":[{"name":"stdout","text":"Random Forest classifier Predictions - [2 2 2 2 1 2 1 2 1 2 2 2 2 2 2 2 1 1 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 1 1 2\n 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2]\n","output_type":"stream"}]},{"cell_type":"code","source":"print('Support Vector Machine classifier predictions - ', predictions_2)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.541856Z","iopub.execute_input":"2022-10-29T17:50:11.542187Z","iopub.status.idle":"2022-10-29T17:50:11.551564Z","shell.execute_reply.started":"2022-10-29T17:50:11.542157Z","shell.execute_reply":"2022-10-29T17:50:11.550322Z"},"trusted":true},"execution_count":77,"outputs":[{"name":"stdout","text":"Support Vector Machine classifier predictions - [2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2\n 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2]\n","output_type":"stream"}]},{"cell_type":"code","source":"print('K nearest neighbor classifier Predictions - ', predictions_3)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.553560Z","iopub.execute_input":"2022-10-29T17:50:11.553904Z","iopub.status.idle":"2022-10-29T17:50:11.561796Z","shell.execute_reply.started":"2022-10-29T17:50:11.553877Z","shell.execute_reply":"2022-10-29T17:50:11.560696Z"},"trusted":true},"execution_count":78,"outputs":[{"name":"stdout","text":"K nearest neighbor classifier Predictions - [2 2 2 2 1 2 2 2 1 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 2\n 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2]\n","output_type":"stream"}]},{"cell_type":"code","source":"from sklearn.metrics import PrecisionRecallDisplay\n\ndisplay = PrecisionRecallDisplay.from_estimator(\n svmclass, X_test, y_test, name=\"LinearSVC\"\n)\n_ = display.ax_.set_title(\"Precision-Recall curve\")","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.563260Z","iopub.execute_input":"2022-10-29T17:50:11.563896Z","iopub.status.idle":"2022-10-29T17:50:11.786517Z","shell.execute_reply.started":"2022-10-29T17:50:11.563864Z","shell.execute_reply":"2022-10-29T17:50:11.785340Z"},"trusted":true},"execution_count":79,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"code","source":"import sklearn","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.787754Z","iopub.execute_input":"2022-10-29T17:50:11.788081Z","iopub.status.idle":"2022-10-29T17:50:11.793545Z","shell.execute_reply.started":"2022-10-29T17:50:11.788052Z","shell.execute_reply":"2022-10-29T17:50:11.792261Z"},"trusted":true},"execution_count":80,"outputs":[]},{"cell_type":"code","source":"#precision score\n\nprecision_score_1 = sklearn.metrics.precision_score(y_test, predictions_1, labels=randforest.classes_)\nprecision_score_2 = sklearn.metrics.precision_score(y_test, predictions_2, labels=svmclass.classes_)\nprecision_score_3 = sklearn.metrics.precision_score(y_test, predictions_3, labels=knnclass.classes_)\n\nprint(\"Precision score for Random Forest Classifier is \", precision_score_1)\nprint(\"Precision score for Support Vector Machine classifier is \", precision_score_2)\nprint(\"Precision score for K nearest neighbor classifier is \", precision_score_3)\n\n","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.794958Z","iopub.execute_input":"2022-10-29T17:50:11.795324Z","iopub.status.idle":"2022-10-29T17:50:11.809122Z","shell.execute_reply.started":"2022-10-29T17:50:11.795293Z","shell.execute_reply":"2022-10-29T17:50:11.808227Z"},"trusted":true},"execution_count":81,"outputs":[{"name":"stdout","text":"Precision score for Random Forest Classifier is 0.625\nPrecision score for Support Vector Machine classifier is 0.0\nPrecision score for K nearest neighbor classifier is 0.75\n","output_type":"stream"}]},{"cell_type":"code","source":"F1_randforest = sklearn.metrics.f1_score(y_test, predictions_1, labels=randforest.classes_, pos_label=1, average='weighted', sample_weight=None)\n\nF1_svmclass = sklearn.metrics.f1_score(y_test, predictions_2, labels=svmclass.classes_, pos_label=1, average='weighted', sample_weight = None)\n\nF1_knnclass = sklearn.metrics.f1_score(y_test, predictions_3, labels=knnclass.classes_, pos_label=1, average='weighted', sample_weight = None)\n\nprint(\"F1 Score for Random Forest Classifier is \", F1_randforest)\nprint(\"F1 Score for Support Vector Machine classifier is \", F1_svmclass)\nprint(\"F1 Score for K nearest neighbor classifier is \", F1_knnclass)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.810332Z","iopub.execute_input":"2022-10-29T17:50:11.810616Z","iopub.status.idle":"2022-10-29T17:50:11.821854Z","shell.execute_reply.started":"2022-10-29T17:50:11.810590Z","shell.execute_reply":"2022-10-29T17:50:11.821079Z"},"trusted":true},"execution_count":82,"outputs":[{"name":"stdout","text":"F1 Score for Random Forest Classifier is 0.9032258064516129\nF1 Score for Support Vector Machine classifier is 0.8109010011123471\nF1 Score for K nearest neighbor classifier is 0.8888248847926267\n","output_type":"stream"}]},{"cell_type":"code","source":"from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay\nfrom sklearn.svm import SVC\n\n\ncm = confusion_matrix(y_test, predictions_2, labels=svmclass.classes_)\ndisp = ConfusionMatrixDisplay(confusion_matrix=cm,\n display_labels=svmclass.classes_)\ndisp.plot()\n","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.822986Z","iopub.execute_input":"2022-10-29T17:50:11.823560Z","iopub.status.idle":"2022-10-29T17:50:11.995991Z","shell.execute_reply.started":"2022-10-29T17:50:11.823527Z","shell.execute_reply":"2022-10-29T17:50:11.994399Z"},"trusted":true},"execution_count":83,"outputs":[{"execution_count":83,"output_type":"execute_result","data":{"text/plain":"<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7f1708692910>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 2 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"code","source":"from sklearn import metrics\n\naccuracy_1 = metrics.accuracy_score(y_test,predictions_1)\nprint('Accuracy for Random Forest classifier model is - ', accuracy_1)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:11.997733Z","iopub.execute_input":"2022-10-29T17:50:11.999371Z","iopub.status.idle":"2022-10-29T17:50:12.006831Z","shell.execute_reply.started":"2022-10-29T17:50:11.999321Z","shell.execute_reply":"2022-10-29T17:50:12.005690Z"},"trusted":true},"execution_count":84,"outputs":[{"name":"stdout","text":"Accuracy for Random Forest classifier model is - 0.9032258064516129\n","output_type":"stream"}]},{"cell_type":"code","source":"accuracy_2 = metrics.accuracy_score(y_test,predictions_2)\nprint('Accuracy for Support Vector Machine classifier model is - ', accuracy_2)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.008769Z","iopub.execute_input":"2022-10-29T17:50:12.009724Z","iopub.status.idle":"2022-10-29T17:50:12.019731Z","shell.execute_reply.started":"2022-10-29T17:50:12.009621Z","shell.execute_reply":"2022-10-29T17:50:12.017699Z"},"trusted":true},"execution_count":85,"outputs":[{"name":"stdout","text":"Accuracy for Support Vector Machine classifier model is - 0.8709677419354839\n","output_type":"stream"}]},{"cell_type":"code","source":"accuracy_3 = metrics.accuracy_score(y_test,predictions_3)\nprint('Accuracy for K nearest neighbor classifier model is - ', accuracy_3)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.021083Z","iopub.execute_input":"2022-10-29T17:50:12.022230Z","iopub.status.idle":"2022-10-29T17:50:12.030196Z","shell.execute_reply.started":"2022-10-29T17:50:12.022190Z","shell.execute_reply":"2022-10-29T17:50:12.029091Z"},"trusted":true},"execution_count":86,"outputs":[{"name":"stdout","text":"Accuracy for K nearest neighbor classifier model is - 0.9032258064516129\n","output_type":"stream"}]},{"cell_type":"markdown","source":"There might be some problem with the data","metadata":{}},{"cell_type":"code","source":"y.value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.031412Z","iopub.execute_input":"2022-10-29T17:50:12.031733Z","iopub.status.idle":"2022-10-29T17:50:12.044268Z","shell.execute_reply.started":"2022-10-29T17:50:12.031704Z","shell.execute_reply":"2022-10-29T17:50:12.043013Z"},"trusted":true},"execution_count":87,"outputs":[{"execution_count":87,"output_type":"execute_result","data":{"text/plain":"2 270\n1 39\nName: LUNG_CANCER, dtype: int64"},"metadata":{}}]},{"cell_type":"code","source":"brf = BalancedRandomForestClassifier(n_estimators = 100, random_state = 0)\n","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.045897Z","iopub.execute_input":"2022-10-29T17:50:12.046395Z","iopub.status.idle":"2022-10-29T17:50:12.052212Z","shell.execute_reply.started":"2022-10-29T17:50:12.046362Z","shell.execute_reply":"2022-10-29T17:50:12.051292Z"},"trusted":true},"execution_count":88,"outputs":[]},{"cell_type":"code","source":"brf.fit(X_train, y_train)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.058124Z","iopub.execute_input":"2022-10-29T17:50:12.058456Z","iopub.status.idle":"2022-10-29T17:50:12.309657Z","shell.execute_reply.started":"2022-10-29T17:50:12.058426Z","shell.execute_reply":"2022-10-29T17:50:12.308507Z"},"trusted":true},"execution_count":89,"outputs":[{"execution_count":89,"output_type":"execute_result","data":{"text/plain":"BalancedRandomForestClassifier(random_state=0)"},"metadata":{}}]},{"cell_type":"code","source":"print(\"F1 score is \",sklearn.metrics.f1_score(y_test, brf.predict(X_test)))","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.311276Z","iopub.execute_input":"2022-10-29T17:50:12.312046Z","iopub.status.idle":"2022-10-29T17:50:12.341073Z","shell.execute_reply.started":"2022-10-29T17:50:12.311982Z","shell.execute_reply":"2022-10-29T17:50:12.340283Z"},"trusted":true},"execution_count":90,"outputs":[{"name":"stdout","text":"F1 score is 0.6666666666666666\n","output_type":"stream"}]},{"cell_type":"code","source":"pre_score = sklearn.metrics.precision_score(y_test, brf.predict(X_test))\nprint(\"Precision score is \", pre_score)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.342400Z","iopub.execute_input":"2022-10-29T17:50:12.342719Z","iopub.status.idle":"2022-10-29T17:50:12.370838Z","shell.execute_reply.started":"2022-10-29T17:50:12.342691Z","shell.execute_reply":"2022-10-29T17:50:12.369718Z"},"trusted":true},"execution_count":91,"outputs":[{"name":"stdout","text":"Precision score is 0.5\n","output_type":"stream"}]},{"cell_type":"code","source":"\ncm = confusion_matrix(y_test, brf.predict(X_test), labels=brf.classes_)\ndisp = ConfusionMatrixDisplay(confusion_matrix=cm,\n display_labels=brf.classes_)\ndisp.plot()","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.372611Z","iopub.execute_input":"2022-10-29T17:50:12.373179Z","iopub.status.idle":"2022-10-29T17:50:12.558274Z","shell.execute_reply.started":"2022-10-29T17:50:12.373139Z","shell.execute_reply":"2022-10-29T17:50:12.557045Z"},"trusted":true},"execution_count":92,"outputs":[{"execution_count":92,"output_type":"execute_result","data":{"text/plain":"<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7f170853dfd0>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 2 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"code","source":"from collections import Counter\nfrom sklearn.datasets import make_classification\nfrom imblearn.over_sampling import RandomOverSampler\n\n#y labels are - 270: 39 (divide both by 309 to get weights)\nX, y = make_classification(n_classes = 2, class_sep = 2, weights = [0.87, 0.12], \n n_informative = 3, n_redundant = 1, flip_y = 0, n_features = 20,\n n_clusters_per_class = 1, n_samples = 309, random_state = 10)\n\nprint('Orignal dataset shape %s' % Counter(y))","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.559560Z","iopub.execute_input":"2022-10-29T17:50:12.560548Z","iopub.status.idle":"2022-10-29T17:50:12.571985Z","shell.execute_reply.started":"2022-10-29T17:50:12.560501Z","shell.execute_reply":"2022-10-29T17:50:12.570872Z"},"trusted":true},"execution_count":93,"outputs":[{"name":"stdout","text":"Orignal dataset shape Counter({0: 270, 1: 39})\n","output_type":"stream"}]},{"cell_type":"code","source":"ros = RandomOverSampler(random_state = 42)\nX_res, y_res = ros.fit_resample(X, y)\n\nprint('Reshaped dataset shape %s' % Counter(y_res))","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.572959Z","iopub.execute_input":"2022-10-29T17:50:12.573468Z","iopub.status.idle":"2022-10-29T17:50:12.585284Z","shell.execute_reply.started":"2022-10-29T17:50:12.573434Z","shell.execute_reply":"2022-10-29T17:50:12.584096Z"},"trusted":true},"execution_count":94,"outputs":[{"name":"stdout","text":"Reshaped dataset shape Counter({0: 270, 1: 270})\n","output_type":"stream"}]},{"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(X_res, y_res, random_state = 42, test_size = 0.2, stratify = y_res)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.587436Z","iopub.execute_input":"2022-10-29T17:50:12.587909Z","iopub.status.idle":"2022-10-29T17:50:12.595758Z","shell.execute_reply.started":"2022-10-29T17:50:12.587856Z","shell.execute_reply":"2022-10-29T17:50:12.594759Z"},"trusted":true},"execution_count":95,"outputs":[]},{"cell_type":"code","source":"model = RandomForestClassifier() \nmodel.fit(X_train, y_train)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.597230Z","iopub.execute_input":"2022-10-29T17:50:12.597539Z","iopub.status.idle":"2022-10-29T17:50:12.780253Z","shell.execute_reply.started":"2022-10-29T17:50:12.597512Z","shell.execute_reply":"2022-10-29T17:50:12.779221Z"},"trusted":true},"execution_count":96,"outputs":[{"execution_count":96,"output_type":"execute_result","data":{"text/plain":"RandomForestClassifier()"},"metadata":{}}]},{"cell_type":"code","source":"predictions = model.predict(X_test)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.781413Z","iopub.execute_input":"2022-10-29T17:50:12.781705Z","iopub.status.idle":"2022-10-29T17:50:12.802614Z","shell.execute_reply.started":"2022-10-29T17:50:12.781678Z","shell.execute_reply":"2022-10-29T17:50:12.801360Z"},"trusted":true},"execution_count":97,"outputs":[]},{"cell_type":"code","source":"model_precision_score = sklearn.metrics.precision_score(y_test, predictions, labels=model.classes_)\nprint(\"Precision score after using Balanced Random Forest Classifier is \", model_precision_score)","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.804431Z","iopub.execute_input":"2022-10-29T17:50:12.805161Z","iopub.status.idle":"2022-10-29T17:50:12.811143Z","shell.execute_reply.started":"2022-10-29T17:50:12.805126Z","shell.execute_reply":"2022-10-29T17:50:12.810344Z"},"trusted":true},"execution_count":98,"outputs":[{"name":"stdout","text":"Precision score after using Balanced Random Forest Classifier is 0.9642857142857143\n","output_type":"stream"}]},{"cell_type":"code","source":"print(\"F1 score after Balanced Random Forest Classifier is \",sklearn.metrics.f1_score(y_test, model.predict(X_test)))","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.812272Z","iopub.execute_input":"2022-10-29T17:50:12.812919Z","iopub.status.idle":"2022-10-29T17:50:12.840012Z","shell.execute_reply.started":"2022-10-29T17:50:12.812887Z","shell.execute_reply":"2022-10-29T17:50:12.838908Z"},"trusted":true},"execution_count":99,"outputs":[{"name":"stdout","text":"F1 score after Balanced Random Forest Classifier is 0.9818181818181818\n","output_type":"stream"}]},{"cell_type":"code","source":"#Confusion Matrix\n\ncm = confusion_matrix(y_test, model.predict(X_test), labels=model.classes_)\ndisp = ConfusionMatrixDisplay(confusion_matrix=cm,\n display_labels=model.classes_)\ndisp.plot()","metadata":{"execution":{"iopub.status.busy":"2022-10-29T17:50:12.841432Z","iopub.execute_input":"2022-10-29T17:50:12.841765Z","iopub.status.idle":"2022-10-29T17:50:13.019922Z","shell.execute_reply.started":"2022-10-29T17:50:12.841734Z","shell.execute_reply":"2022-10-29T17:50:13.018529Z"},"trusted":true},"execution_count":100,"outputs":[{"execution_count":100,"output_type":"execute_result","data":{"text/plain":"<sklearn.metrics._plot.confusion_matrix.ConfusionMatrixDisplay at 0x7f17084da2d0>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 2 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]}]}