/*******************************************************************************************************************
-- Title : [Py3.5] Using IRIS Dataset w/ Scikit-Learn
-- Reference : stackoverflow.com/questions/38105539
-- Key word : sklearn scikit-learn iris dataset dataframe
*******************************************************************************************************************/
■ Scripts
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 | import numpy as np import pandas as pd from sklearn.datasets import load_iris # ------------------------------ # -- Set Dataframe Option # ------------------------------ pd.set_option('display.height', 1000) pd.set_option('display.max_rows', 500) pd.set_option('display.max_columns', 500) pd.set_option('display.width', 1000) # ------------------------------ # -- iris dataset # ------------------------------ # save load_iris() sklearn dataset to iris # if you'd like to check dataset type use: type(load_iris()) # if you'd like to view list of attributes use: dir(load_iris()) iris = load_iris() print(type(load_iris())) print("... type", "." * 100, "\n") print(dir(load_iris())) print("... dir", "." * 100, "\n") print(iris['feature_names']) print("... feature_names", "." * 100, "\n") print(iris['target']) print("... target", "." * 100, "\n") # ------------------------------ # -- change iris dataset to dataframe # ------------------------------ # np.c_ is the numpy concatenate function # which is used to concat iris['data'] and iris['target'] arrays # for pandas column argument: concat iris['feature_names'] list # and string list (in this case one string); you can make this anything you'd like.. # the original dataset would probably call this ['Species'] data1 = pd.DataFrame(data= np.c_[iris['data'], iris['target']], columns= iris['feature_names'] + ['target']) print (data1.head()) print(",,, dataframe from load_iris()", "," * 100, "\n") | cs |