import pandas as pd
import matplotlib.pyplot as plt

import umb_tools as umb

# konfiguracja
plt.rcParams["figure.figsize"] = [5, 4]
pd.set_option("display.float_format", lambda x: "%.4f" % x)

# odczyt pliku TSV (zwracane są: zbiór danych w postaci DataFrame biblioteki Pandas oraz lista nazw klas)

(df, c_names) = umb.read_data("data/BreastCancer.txt")
df

# pobranie dwóch cech z macierzy danych
data = df.iloc[:, [1, 10]]

data.describe()

from sklearn.preprocessing import StandardScaler

data = df.iloc[:, [1, 10]]

norm_data = StandardScaler().fit_transform(data)

pd.DataFrame(norm_data, columns=data.columns).describe()

from sklearn.preprocessing import MinMaxScaler

data = df.iloc[:, [1, 10]]

norm_data = MinMaxScaler().fit_transform(data)

pd.DataFrame(norm_data, columns=data.columns).describe()

# pobranie etykiet klas
labels = df.iloc[:, 0].to_numpy()

# pobranie macierzy danych
data = df.iloc[:, 1:].to_numpy()

# standaryzacja
data_norm = StandardScaler().fit_transform(data)

# wykresy PCA 
fig, ax = plt.subplots(1, 2, figsize=(10, 4))

umb.pca_plot(data, labels, c_names, ax[0], "Without standarization")
umb.pca_plot(data_norm, labels, c_names, ax[1], "With standarization")

plt.show()

#BreastCancer	labels	radius_mean	texture_mean	perimeter_mean	area_mean	smoothness_mean	compactness_mean	concavity_mean	concave points_mean	symmetry_mean	...	radius_worst	texture_worst	perimeter_worst	area_worst	smoothness_worst	compactness_worst	concavity_worst	concave points_worst	symmetry_worst	fractal_dimension_worst
842302	1	17.9900	10.3800	122.8000	1001.0000	0.1184	0.2776	0.3001	0.1471	0.2419	...	25.3800	17.3300	184.6000	2019.0000	0.1622	0.6656	0.7119	0.2654	0.4601	0.1189
874858	1	14.2200	23.1200	94.3700	609.9000	0.1075	0.2413	0.1981	0.0662	0.2384	...	15.7400	37.1800	106.4000	762.4000	0.1533	0.9327	0.8488	0.1772	0.5166	0.1446
875263	1	12.3400	26.8600	81.1500	477.4000	0.1034	0.1353	0.1085	0.0456	0.1943	...	15.6500	39.3400	101.7000	768.9000	0.1785	0.4706	0.4425	0.1459	0.3215	0.1205
87556202	1	14.8600	23.2100	100.4000	671.4000	0.1044	0.1980	0.1697	0.0888	0.1737	...	16.0800	27.7800	118.6000	784.7000	0.1316	0.4648	0.4589	0.1727	0.3000	0.0870
875938	1	13.7700	22.2900	90.6300	588.9000	0.1200	0.1267	0.1385	0.0653	0.1834	...	16.3900	34.0100	111.6000	806.9000	0.1737	0.3122	0.3809	0.1673	0.3080	0.0933
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
8910720	2	10.7100	20.3900	69.5000	344.9000	0.1082	0.1289	0.0845	0.0287	0.1668	...	11.6900	25.2100	76.5100	410.4000	0.1335	0.2550	0.2534	0.0860	0.2605	0.0870
8910506	2	12.8700	16.2100	82.3800	512.2000	0.0943	0.0622	0.0390	0.0162	0.2010	...	13.9000	23.6400	89.2700	597.5000	0.1256	0.1808	0.1992	0.0578	0.3604	0.0706
8910499	2	13.5900	21.8400	87.1600	561.0000	0.0796	0.0826	0.0407	0.0214	0.1635	...	14.8000	30.0400	97.6600	661.5000	0.1005	0.1730	0.1453	0.0619	0.2446	0.0702
8912055	2	11.7400	14.0200	74.2400	427.3000	0.0781	0.0434	0.0225	0.0276	0.2101	...	13.3100	18.2600	84.7000	533.7000	0.1036	0.0850	0.0673	0.0829	0.3101	0.0669
92751	2	7.7600	24.5400	47.9200	181.0000	0.0526	0.0436	0.0000	0.0000	0.1587	...	9.4560	30.3700	59.1600	268.6000	0.0900	0.0644	0.0000	0.0000	0.2871	0.0704

#BreastCancer	radius_mean	fractal_dimension_mean
count	569.0000	569.0000
mean	14.1273	0.0628
std	3.5240	0.0071
min	6.9810	0.0500
25%	11.7000	0.0577
50%	13.3700	0.0615
75%	15.7800	0.0661
max	28.1100	0.0974

#BreastCancer	radius_mean	fractal_dimension_mean
count	569.0000	569.0000
mean	-0.0000	0.0000
std	1.0009	1.0009
min	-2.0296	-1.8199
25%	-0.6894	-0.7226
50%	-0.2151	-0.1783
75%	0.4694	0.4710
max	3.9713	4.9109

#BreastCancer	radius_mean	fractal_dimension_mean
count	569.0000	569.0000
mean	0.3382	0.2704
std	0.1668	0.1487
min	0.0000	0.0000
25%	0.2233	0.1630
50%	0.3024	0.2439
75%	0.4164	0.3404
max	1.0000	1.0000

UMB W05: przetwarzanie wstępne¶

1. Wczytanie zbioru danych¶

2. Normalizacja danych¶