Das deutsche Python-Forum

Code: Alles auswählen

# -*- coding: utf-8 -*-

from sklearn import tree
import pandas as pd
import numpy as np


names=['Category','Hour','Minutes','Seconds','Yaer','Month','Day','x_grid', 'y_grid']
crimeDataSet = pd.read_csv('crimeDataSet.csv', sep=';', names=names, dtype={'x_grid':np.float64, 'y_grid':np.float64})

Code: Alles auswählen

# -*- coding: utf-8 -*-

from pandas import DataFrame, Series
import pandas as pd
import numpy as np
import matplotlib.pylab as plt
from sklearn.cross_validation import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import classification_report
import sklearn.metrics
[b]#Load the dataset[/b]
header=['Hour','Year','Month','Day','x_grid', 'y_grid','Category']
myData=pd.read_csv('crimeDataSet.csv', sep=';')


data_clean=myData.dropna()
print (data_clean.dtypes)
print(data_clean.describe())

predictors=data_clean[['Hour','Year','Month','Day','x_grid', 'y_grid']]
targets=data_clean.Category

pred_train, pred_test, tar_train,tar_test=train_test_split(predictors, targets, test_size=.4)

print(pred_train.shape)
print(pred_test.shape)
print(tar_train.shape)
print(tar_test.shape)
[b]
#Build a model on training data[/b]

classifier= DecisionTreeClassifier()
classifier= classifier.fit(pred_train,tar_train)

predictions=classifier.predict(pred_test)
print(sklearn.metrics.confusion_matrix(tar_test,predictions))
print(sklearn.metrics.accuracy_score(tar_test,predictions))


[b]#Display a decision tree[/b]
from sklearn import tree
from io import StringIO
from IPython.display import Image 
import pydotplus
dot_data=StringIO()
tree.export_graphviz(classifier,out_file=dot_data)
graph=pydotplus.graph_from_dot_data(dot_data.getvalue())
Image(graph.creat_png())
print('fertig')