1
2
3

# dataset为dataframe
dataset.plot(kind='box', subplots=True, layout=(2,2), sharex=False, sharey=False)
plt.show()

1
2
3
4

...
# histograms
dataset.hist()
plt.show()

1
2
3
4
5

from pandas.plotting import scatter_matrix
...
# scatter plot matrix
scatter_matrix(dataset)
plt.show()

1
2
3
4
5
6
7

import matplotlib.pyplot as plt
import seaborn as sns
# dataset is dataframe
correlation = dataset.corr()
# display(correlation)
plt.figure(figsize=(14, 12))
heatmap = sns.heatmap(correlation, annot=True, linewidths=0, vmin=-1, cmap="RdBu_r")

1
2
3
4
5
6
7
8
9
10
11
12
13

#Visualize the co-relation between pH and fixed Acidity

#Create a new dataframe containing only pH and fixed acidity columns to visualize their co-relations
fixedAcidity_pH = dataset[['pH', 'fixed acidity']]

#Initialize a joint-grid with the dataframe, using seaborn library
gridA = sns.JointGrid(x="fixed acidity", y="pH", data=fixedAcidity_pH, size=6)

#Draws a regression plot in the grid
gridA = gridA.plot_joint(sns.regplot, scatter_kws={"s": 10})

#Draws a distribution plot in the same grid
gridA = gridA.plot_marginals(sns.distplot)

1
2
3
4
5
6
7

from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC

1
2
3
4
5
6
7
8
9

from sklearn.model_selection import train_test_split
...
#数据集提取x和y，x对应属性，y对应分类
X_array = dataset.values[:,:4]
y_array = dataset.values[:,4]
#按照1:4获取验证集和训练集
X_train,X_test,y_train,y_test = train_test_split(X_array,y_array,test_size=0.2,shuffle=True)
model= SVC()
model.fit(X_train,y_train)

1
2
3
4
5
6
7
8
9
10
11
12

print(model.score(X_test,y_test))
prediction = model.predict(X_test)
import joblib

# save the model to disk
filename = 'finalized_model.sav'
joblib.dump(model, filename)

# some time later...

# load the model from disk
loaded_model = joblib.load(filename)