{"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_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)\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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"1 - Data Processing","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"2 - Non-Personalized Recommendations","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"3 - Personalized Recommendations","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"4 - PCA code","metadata":{}},{"cell_type":"code","source":"#making own code for calculating the Principal component \ndef PCA(X,XT,m=2):\n    \"\"\"\n    X = traindata\n    XT = testdata\n    m = output dimension\n    \"\"\"\n\n    #calculating standard deviation and mean for each column (feature)\n    mean = np.mean(X,axis=0)\n    std = np.std(X,axis=0)\n    \n    #normalizing all the features did not work. Assuming the dataset is normalized already.\n    #X_norm = (X-mean)/std\n    X_norm=X\n    \n    #creating covariance matrix\n    cov_mat = np.cov(X_norm,rowvar=False)\n   \n\n    #constructing the covariance matrix\n    evals , evecs = np.linalg.eigh(cov_mat)\n    \n    #sorting eigenvalues and eigenvectors from high to low\n    idx = np.argsort(-evals)\n    sorted_evals = evals[idx]\n    sorted_evecs = np.real(evecs[:,idx])\n    \n    #making the wanted number of principal component vectors\n    PCA_vec = sorted_evecs[:,:m]\n    \n    #making projections down to the principal component vectors\n    proj = X_norm@PCA_vec\n    \n    \"\"\"\n    returning the Normalized data, the projection to the m PCAs,\n    eigenvalues and the eigenvectors (sorted).\n    Here X_norm = X since the data already was normalized\n    \"\"\"\n    return proj, sorted_evals, sorted_evecs","metadata":{},"execution_count":null,"outputs":[]}]}