FDC/fdcTool.py

import warnings
warnings.filterwarnings('ignore')

import json

import pandas as pd
import numpy as np

from fdc.visualize import plotCluster
from fdc.tools import Timing
from fdc.missingValues import fix_missing_values
from fdc.fdc import canberra_modified, FDC, Clustering

from fdc.dataSheet import DataSheet

filename='healthcare-dataset-stroke-data.csv'
np.random.seed(42)
tb = DataSheet(filename)
tb.showStatistic()

hasChanged = False
if len(tb.cols_nom) > 0:
  print()
  print("Fixing object datatypes ...")
  tb.fixDatatypes()
  print("done")
  hasChanged = True

if tb.has_missing_values:
  print()
  print("Fix missing values ...")
  tb.fix_missing_values()
  print("done")
  hasChanged = True

if hasChanged:
  print()
  tb.showStatistic()
  tb.saveTable(filename + "_fixed_values.csv")
  tb.saveMapping(filename + "_value_mapping.json")


print("Doing FDC ...")
fdc = FDC(clustering_cont=Clustering('euclidean')
          , clustering_ord=Clustering(canberra_modified)
          , clustering_nom=Clustering('hamming', max_components=1)
          , visual=False
          , use_pandas_output=True
          , with_2d_embedding=False
          )

fdc.selectFeatures(continueous=tb.cols_cont, nomial=tb.cols_nom, ordinal=tb.cols_ord)

entire_data_FDC_emb_five = fdc.normalize(tb.data)
entire_data_FDC_emb_five.to_csv(filename + "_fdc.csv")
print("done")