Pandas与sklearn结合实例

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

df = pd.DataFrame({'Condition 1': np.random.rand(20),
                   'Condition 2': np.random.rand(20) * 0.9,
                   'Condition 3': np.random.rand(20) * 1.1
                  })
df

	Condition 1	Condition 2	Condition 3
0	0.150388	0.319698	0.307660
1	0.969830	0.613011	0.695216
2	0.660890	0.552131	0.229432
3	0.574232	0.679883	0.738781
4	0.527174	0.578460	0.981132
5	0.952754	0.388025	0.935823
6	0.077330	0.331501	0.663525
7	0.288425	0.755113	0.829731
8	0.398153	0.668251	0.674626
9	0.687752	0.540433	0.971847
10	0.470583	0.352360	0.249517
11	0.643588	0.240827	0.640346
12	0.278763	0.012188	0.506313
13	0.486791	0.538330	0.005713
14	0.661333	0.101712	0.868087
15	0.420160	0.640365	0.388247
16	0.932169	0.580433	0.594378
17	0.956558	0.878580	0.458417
18	0.637018	0.058973	0.338527
19	0.950942	0.647577	0.687604

fig,ax = plt.subplots(figsize=(10,8))
#stacked 是否堆叠
df.plot.bar(ax=ax,stacked=False)

<matplotlib.axes._subplots.AxesSubplot at 0xa263898>

from matplotlib.ticker import FuncFormatter

df_ratio = df.div(df.sum(axis=1),axis=0)
fig,ax = plt.subplots()
df_ratio.plot.bar(ax=ax,stacked=True)
ax.yaxis.set_major_formatter(FuncFormatter(lambda y,_:'{:.0%}'.format(y)))

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00383/risk_factors_cervical_cancer.csv'
df = pd.read_csv(url, na_values="?")
df.head()

	Age	Number of sexual partners	First sexual intercourse	Num of pregnancies	Smokes	Smokes (years)	Smokes (packs/year)	Hormonal Contraceptives	Hormonal Contraceptives (years)	IUD	...	STDs: Time since first diagnosis	STDs: Time since last diagnosis	Dx:Cancer	Dx:CIN	Dx:HPV	Dx	Hinselmann	Schiller	Citology	Biopsy
0	18	4.0	15.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	...	NaN	NaN	0	0	0	0	0	0	0	0
1	15	1.0	14.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	...	NaN	NaN	0	0	0	0	0	0	0	0
2	34	1.0	NaN	1.0	0.0	0.0	0.0	0.0	0.0	0.0	...	NaN	NaN	0	0	0	0	0	0	0	0
3	52	5.0	16.0	4.0	1.0	37.0	37.0	1.0	3.0	0.0	...	NaN	NaN	1	0	1	0	0	0	0	0
4	46	3.0	21.0	4.0	0.0	0.0	0.0	1.0	15.0	0.0	...	NaN	NaN	0	0	0	0	0	0	0	0

5 rows × 36 columns

from sklearn.preprocessing import Imputer
#缺失值填充处理
impute =  pd.DataFrame(Imputer().fit_transform(df))
impute.columns = df.columns
impute.index = df.index

impute.head()

	Age	Number of sexual partners	First sexual intercourse	Num of pregnancies	Smokes	Smokes (years)	Smokes (packs/year)	Hormonal Contraceptives	Hormonal Contraceptives (years)	IUD	...	STDs: Time since first diagnosis	STDs: Time since last diagnosis	Dx:Cancer	Dx:CIN	Dx:HPV	Dx	Hinselmann	Schiller	Citology	Biopsy
0	18.0	4.0	15.0000	1.0	0.0	0.0	0.0	0.0	0.0	0.0	...	6.140845	5.816901	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	15.0	1.0	14.0000	1.0	0.0	0.0	0.0	0.0	0.0	0.0	...	6.140845	5.816901	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	34.0	1.0	16.9953	1.0	0.0	0.0	0.0	0.0	0.0	0.0	...	6.140845	5.816901	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	52.0	5.0	16.0000	4.0	1.0	37.0	37.0	1.0	3.0	0.0	...	6.140845	5.816901	1.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0
4	46.0	3.0	21.0000	4.0	0.0	0.0	0.0	1.0	15.0	0.0	...	6.140845	5.816901	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

5 rows × 36 columns

%matplotlib notebook
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.decomposition import PCA
from mpl_toolkits.mplot3d import Axes3D

features = impute.drop('Dx:Cancer', axis=1)
y = impute["Dx:Cancer"]

pca = PCA(n_components=3)
X_r = pca.fit_transform(features)

print("Explained variance:\nPC1 {:.2%}\nPC2 {:.2%}\nPC3 {:.2%}"
      .format(pca.explained_variance_ratio_[0],
              pca.explained_variance_ratio_[1],
              pca.explained_variance_ratio_[2]))

fig = plt.figure()
ax = Axes3D(fig)

ax.scatter(X_r[:, 0], X_r[:, 1], X_r[:, 2], c=y, cmap=plt.cm.coolwarm)

# Label the axes
ax.set_xlabel('PC1')
ax.set_ylabel('PC2')
ax.set_zlabel('PC3')