def CentralAndNorm(self):
     """centralize and normalize the total dataframe
     """
     from centralize_outlier import centralizeOutlier
     from normalize import linearNormalize
     df_to_process = self.total_dt.drop(['mcc'], axis=1)
     centralizeOutlier(df_to_process, devs=3)
     df_to_process = linearNormalize(df_to_process, ceil=1.0, floor=(-1.0))
     
     mcc = df(self.total_dt['mcc'])
     self.total_dt = pd.concat([df_to_process, mcc], axis=1)
Exemple #2
0
    def NormAndCentralize(self, centralized=True):
        mcc = self.all_set[:, 0]
        df_to_process = self.all_set[:, 1:]
        df_to_process = pd.DataFrame(df_to_process)

        if centralized == True:
            centralizeOutlier(df_to_process, devs=self.devs)
            
        df_to_process = linearNormalize(df_to_process, ceil=1.0, floor=-1.0)
        df_to_process = df_to_process.values
        
        self.all_set = np.column_stack((mcc, df_to_process))
Exemple #3
0
    def preSvcData(self, print_it=False):
        """
        collect the data for SVC,
        centralize and normalize all the columns except for mcc,
        user can choose to print the table by setting print_it to True.
        """
        df_to_process = self.svc_sheet.drop(['mcc'], axis=1)

        centralizeOutlier(df_to_process, devs=self.devs)

        df_to_process = linearNormalize(df_to_process, ceil=1.0, floor=-1.0)

        mcc = pd.DataFrame(self.svc_sheet['mcc'])
        self.svc_sheet = pd.concat([df_to_process, mcc], axis=1)
Exemple #4
0
    def preAllData(self, print_it=False, centralized=True):
        """
        for the whole data set:
        centralize and normalize all the columns except for mcc,
        user can choose to print the table by setting print_it to True.
        """
        df_to_process = self.all_sheet.drop(['mcc'], axis=1)

        if centralized == True:
            centralizeOutlier(df_to_process, devs=self.devs)

        df_to_process = linearNormalize(df_to_process, ceil=1.0, floor=-1.0)

        mcc = pd.DataFrame(self.all_sheet['mcc'])
        self.all_sheet = pd.concat([df_to_process, mcc], axis=1)
Exemple #5
0
    def processMccEner(self, centralized=True, normed=True):
        f = h5py.File(self.h5_path)
        dt = f[self.all_path][()]
        f.close()
        
        self.whole_dt = pd.DataFrame(dt)
        self.whole_dt.columns = self.rep_ener_columns
        self.dropWrongMcc()

        
        if centralized == True:
            df_to_process = self.whole_dt.drop(['mcc'], axis=1)
            centralizeOutlier(df_to_process, devs=self.devs)
            
        if normed == True:
            df_to_process = linearNormalize(df_to_process, ceil=1.0, floor=-1.0)
            mcc = pd.DataFrame(self.whole_dt['mcc'])
        
            self.whole_dt = pd.concat([mcc, df_to_process], axis=1)