| docker-ml-python-sandbox - Dockerfile for machine learning environment(scikit-learn, chainer, gensim, tensorflow, jupyter) zuqqhi2/docker-ml-python-sandbox - GitHub |
### Docker Pull docker pull zuqqhi2/ml-python-sandbox:latest docker images #REPOSITORY TAG IMAGE ID CREATED SIZE #zuqqhi2/ml-python-sandbox latest 4402825ff756 2 hours ago 12.9 GB ### Run jupyter without login to container sudo docker run -it -p 8888:8888 zuqqhi2/ml-python-sandbox # access to the host using browser with 8888 port like http://sample.com:8888 ### Login to container sudo docker run -it -p 8888:8888 zuqqhi2/ml-python-sandbox /bin/bash source ~/.bash_profile mlact # Set Japanese env export LANG=ja_JP.UTF-8 export LC_ALL=ja_JP.UTF-8 export LC_CTYPE=ja_JP.UTF-8 ### Run jupyter notebook after login to container jupyter notebook --ip=0.0.0.0 --port=8888
import numpy as np
import pandas as pd
from sklearn.cross_validation import ShuffleSplit, train_test_split
from sklearn.tree import DecisionTreeClassifier, export_graphviz
from sklearn.metrics import f1_score, make_scorer, accuracy_score
from sklearn.grid_search import GridSearchCV
from sklearn import datasets
from pydotplus import graph_from_dot_data
from IPython.display import Image
# Load data
iris = datasets.load_iris()
features = iris.data
categories = iris.target
# Cross-Validation setting
X_train, X_test, y_train, y_test = train_test_split(features, categories, test_size=0.2, random_state=42)
cv_sets = ShuffleSplit(X_train.shape[0], n_iter = 10, test_size = 0.20, random_state = 0)
params = {'max_depth': np.arange(2,11), 'min_samples_leaf': np.array([5])}
# Learning
def performance_metric(y_true, y_predict):
score = f1_score(y_true, y_predict, average='micro')
return score
classifier = DecisionTreeClassifier()
scoring_fnc = make_scorer(performance_metric)
grid = GridSearchCV(classifier, params, cv=cv_sets, scoring=scoring_fnc)
best_clf = grid.fit(X_train, y_train)
# Plot decision tree
dot_data = export_graphviz(best_clf.best_estimator_, out_file=None,
feature_names=iris.feature_names,
class_names=iris.target_names,
filled=True, rounded=True,
special_characters=True)
graph = graph_from_dot_data(dot_data)
Image(graph.create_png())
from MeCab import Tagger
from pyknp import Juman
target_text = u"すもももももももものうち"
m = Tagger("-Owakati")
print("***** Mecab *****")
print(m.parse(target_text))
juman = Juman()
result = juman.analysis(target_text)
print("***** Juman *****")
print(' '.join([mrph.midasi for mrph in result.mrph_list()]))
| はじめにtensorflowやtflearnでモデルを作っていると、ネットワークを図にしたり学習の進み具合をさくっとグラフにしてくれるツールがあると便利だな、と思ったことがあると思います。Googleで検索をしているとtensorboardなるものを見つけたので、こちらを使って見たいと思います。ちなみに、この記事の内容は以下のDockerイメージを使うことでさくっと試すことができます。環境ニューラルネットワークを簡単に作りたかったので、tflearnを使いました。OS : Ubuntu 16.04python : 3.5.2tensorflow : 1.1.0tfLearn : 0.3tensorboard : ... Tensorboardを使ってニューラルネットワークと学習の状況を可視化する - zuqqhi2 Tech Memo |
View Comments
I do like the way you have presented this challenge plus it really does supply me a lot of fodder for thought. Nevertheless, from everything that I have personally seen, I really trust when the feed-back stack on that people today continue to be on point and don't embark on a tirade associated with the news du jour. Anyway, thank you for this exceptional piece and even though I can not really agree with this in totality, I respect your perspective.