Experiment-8 Complete

from numpy import isnan
from pandas import read_csv
from sklearn.impute import SimpleImputer

url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/horse-colic.csv"
dataframe = read_csv(url, header = None, na_values = '?')
data = dataframe.values
for i in range(dataframe.shape[1]):
    n_miss = dataframe[[i]].isnull().sum()
    perc = n_miss / dataframe.shape[0] * 100
    print("> %d, Missing: %d (%.lf%%)" % (i, n_miss, perc))
imputer = SimpleImputer(strategy = "mean")
imputer.fit(data)
Xtrans = imputer.transform(data)
print("Missing: %d"%sum(isnan(Xtrans).flatten()))

#NEXT CELL

from numpy import isnan
from pandas import read_csv
from sklearn.impute import KNNImputer

url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/horse-colic.csv"
dataframe = read_csv(url, header = None, na_values = '?')
data = dataframe.values
for i in range(dataframe.shape[1]):
    n_miss = dataframe[[i]].isnull().sum()
    perc = n_miss / dataframe.shape[0] * 100
    print("> %d, Missing: %d (%.lf%%)" % (i, n_miss, perc))
imputer = KNNImputer()
imputer.fit(data)
Xtrans = imputer.transform(data)
print("Missing: %d"%sum(isnan(Xtrans).flatten()))

# NEXT CELL

from numpy import isnan
from pandas import read_csv
from sklearn.experimental import enable_iterative_imputer
from sklearn.impute import IterativeImputer

url = "https://raw.githubusercontent.com/jbrownlee/Datasets/master/horse-colic.csv"
dataframe = read_csv(url, header = None, na_values = '?')
data = dataframe.values
for i in range(dataframe.shape[1]):
    n_miss = dataframe[[i]].isnull().sum()
    perc = n_miss / dataframe.shape[0] * 100
    print("> %d, Missing: %d (%.lf%%)" % (i, n_miss, perc))
imputer = IterativeImputer()
imputer.fit(data)
Xtrans = imputer.transform(data)
print("Missing: %d"%sum(isnan(Xtrans).flatten()))