{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../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\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import gc\nimport cv2\nfrom PIL import Image\nimport matplotlib.pyplot as plt\n\n###########################################################################\n\nfrom tqdm import tqdm\n\n#########################################################################\n\nimport lightgbm  as lgb\nimport catboost as cbt\nimport xgboost as xgb\nimport sklearn.ensemble as ensem\nimport sklearn.linear_model as lm\nimport sklearn.svm as svm \nimport sklearn.neighbors as neibs\nimport sklearn.naive_bayes  as nb\nimport sklearn.discriminant_analysis as danl \n\n##########################################################\n\nimport sklearn.metrics as metrics\nfrom sklearn.model_selection import train_test_split\nfrom keras.preprocessing.image import ImageDataGenerator\n\n##########################################################\n\nimport sklearn.decomposition as decomp\nimport sklearn.manifold as mnfld","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/train.csv')\ntest = pd.read_csv('../input/test.csv')\nimgsize = 14\nimgsize2 = 196\nimages = []\npaths = train.id_code\nfor path in paths :\n    img = cv2.imread(f'../input/train_images/{path}.png')\n    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n    img = cv2.resize(img,(imgsize,imgsize),interpolation=cv2.INTER_CUBIC)\n    img = (img.reshape((imgsize2,))/255).tolist()\n    images.append(img)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainxdf =  pd.DataFrame(images)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#kernel : \"linear\" | \"poly\" | \"rbf\" | \"sigmoid\"\n#kernel  | \"cosine\" | \"precomputed\"\nkpcatrain = decomp.KernelPCA(n_components=8,\n                            kernel=\"poly\",\n                            gamma=None, \n                            degree=3, \n                            coef0=1,\n                            kernel_params=None,\n                            alpha=0.1, \n                            fit_inverse_transform=False, \n                            eigen_solver='auto',\n                            tol=0,\n                            max_iter=None,\n                            remove_zero_eig=False,\n                            random_state=0\n                          )\n\ncolskpca = [\"kpca1\",\"kpca2\",\"kpca3\",\"kpca4\",\"kpca5\",\n           \"kpca6\",\"kpca7\",\"kpca8\"]\nkpcatraindf =  pd.DataFrame(kpcatrain.fit_transform(trainxdf),\n                            columns=colskpca)\n\ntrainxdf =  pd.concat([trainxdf,kpcatraindf], axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rf = ensem.RandomForestClassifier(n_estimators=2000,\n                                  max_depth=200,\n                                  random_state=100)\nrf.fit(trainxdf,train.diagnosis)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"imgsize = 14\nimgsize2 = 196\nimagest = []\npaths = test.id_code\nfor path in paths :\n    img = cv2.imread(f'../input/test_images/{path}.png')\n    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n    img = cv2.resize(img,(imgsize,imgsize),interpolation=cv2.INTER_CUBIC)\n    img = (img.reshape((imgsize2,))/255).tolist()\n    imagest.append(img)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"testxdf =  pd.DataFrame(imagest)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"########################################################################\n\nkpcatest = decomp.KernelPCA(n_components=8,\n                            kernel=\"poly\",\n                            gamma=None, \n                            degree=3, \n                            coef0=1,\n                            kernel_params=None,\n                            alpha=0.1, \n                            fit_inverse_transform=False, \n                            eigen_solver='auto',\n                            tol=0,\n                            max_iter=None,\n                            remove_zero_eig=False,\n                            random_state=0\n                          )\n\ncolskpca = [\"kpca1\",\"kpca2\",\"kpca3\",\"kpca4\",\"kpca5\",\n           \"kpca6\",\"kpca7\",\"kpca8\"]\nkpcatestdf =  pd.DataFrame(kpcatest.fit_transform(testxdf),\n                           columns=colskpca)\ntestxdf =  pd.concat([testxdf,kpcatestdf], axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predVal = rf.predict(testxdf)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test['diagnosis'] = predVal\ntest.to_csv(\"submission.csv\",index=False, header=True)","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":1}