Skip to content
Snippets Groups Projects
PCA_.py 3.16 KiB
Newer Older
DIANE's avatar
DIANE committed
from sklearn.decomposition import PCA
DIANE's avatar
DIANE committed

class LinearPCA:
DIANE's avatar
DIANE committed
    def __init__(self, X, Ncomp=10):
        ## define color palette to use for plotting
DIANE's avatar
DIANE committed
        #self.__palette = 'YlGn'
        #numerical_data, categorical_data, scaled_values = col_cat(X)
        #self.catdata = list(categorical_data.columns)
DIANE's avatar
DIANE committed


DIANE's avatar
DIANE committed
        ## input matrix
DIANE's avatar
DIANE committed
        self.__x = X
DIANE's avatar
DIANE committed
        self._varnames = X.columns
        self._rownames = X.index
DIANE's avatar
DIANE committed

DIANE's avatar
DIANE committed
        ## set the number of components to compute and fit the model
        self.__ncp = Ncomp
        M = PCA(n_components = self.__ncp)
        M.fit(self.__x)
DIANE's avatar
DIANE committed

DIANE's avatar
DIANE committed
        ######## results ########
        # Explained variability
        
        self.__pcnames = [f'PC{i+1}({100 *  M.explained_variance_ratio_[i].round(2)}%)' for i in range(self.__ncp)]
        
        self._Qexp_ratio = pd.DataFrame(100 *  M.explained_variance_ratio_, columns = ["Qexp"], index= [f'PC{i+1}' for i in range(self.__ncp)])
        # Loadings and scores
         #scores
        s = M.transform(self.__x)
        self.__t = s
        self._t = s
        self._r = pd.DataFrame(2*(s-s.min(axis=0))/(s.max(axis=0)-s.min(axis=0)) -1, index= self._rownames)
        self._r.columns = self.__pcnames

        # Normalize each loading vector to have unit length
        self._p = (M.components_ / np.linalg.norm(M.components_, axis=0)).T
        
        # Matrix reconstruction or prediction making
        #
        self.res = pd.DataFrame()
        for i in range(self.__ncp):
            self._xp = np.dot(self.__t[:,i].reshape((-1,1)), self._p[:,i].reshape((1,-1)))
            # residuals
            self._e = self.__x - self._xp
            self.res[self.__pcnames[i]] = np.diag(self._e@self._e.T)
            #self._res = pd.DataFrame( self._e, columns = self._varnames, index = self._rownames )
        
        self._xp = self.__t @ self._p.T

        # Compute the cosine similarity between the normalized loading vectors
        self.lev = {}
        ## Laverage: leverage values range between 0 and 1
        for i in range(self._t.shape[1]):
            ti = self._t[:,i].reshape((-1,1))
            Hat = ti @ np.linalg.pinv(np.transpose(ti) @ ti) @ np.transpose(ti)
            self.lev[self._r.columns[i]] = ti.ravel()
        self.leverage = pd.DataFrame(self.lev)

DIANE's avatar
DIANE committed
        ## Hotelling t2
        
        self.eigvals = M.singular_values_**2
        self.Lambda = np.diag(self.eigvals)
        self.T2 = pd.DataFrame()
        tt = self._r.to_numpy()
        for i in range(self._t.shape[1]):
           self.T2[self.__pcnames[i]] = np.diag(self.__t[:,i].reshape((-1,1)) @ np.linalg.inv(np.array(self.Lambda[i,i]).reshape((1,1))) @ np.transpose(self.__t[:,i].reshape((-1,1))))
DIANE's avatar
DIANE committed
        

    @property
    def scores_(self):
        return pd.DataFrame(self._r)
    
    @property
    def loadings_(self):
        return pd.DataFrame(self._p, columns=self.__pcnames, index=self._varnames)
    
    @property
    def leverage_(self):
        return self.leverage
    
    @property
    def residuals(self):
DIANE's avatar
DIANE committed
        return self.res
    @property
    def hotelling(self):
        #return pd.DataFrame(self.T2)
        return self.T2