| fscore = [ (v,k) for k,v in clf.get_fscore().iteritems() ] | |
| fscore.sort(reverse=True) |
| import pandas as pd | |
| import matplotlib.pyplot as plt | |
| import seaborn as sns | |
| sns.set() | |
| scores = pd.read_csv('liberty-mutual-group-property-inspection-prediction_public_leaderboard.csv') | |
| scores['SubmissionDate'] = [time.date() for time in scores['SubmissionDate'].astype('datetime64[ns]')] | |
| scores['SubmissionDate'] = [time for time in scores['SubmissionDate'].astype(str)] |
| plt.style.use('bmh') | |
| colors = ['#348ABD', '#A60628', '#7A68A6', '#467821', '#D55E00', | |
| '#CC79A7', '#56B4E9', '#009E73', '#F0E442', '#0072B2'] | |
| https://github.com/rasbt/matplotlib-gallery |
| import pandas as pd | |
| pd.set_option('display.mpl_style', 'default') | |
| pd.set_option('display.width', 200) | |
| pd.set_option('display.max_columns', 20) | |
| pd.set_option('display.max_rows', 50) | |
| pd.set_option('precision', 5) | |
| import matplotlib.pyplot as plt | |
| import seaborn as sns |
| thisField.setValue(0) |
| # http://www.dataiku.com/blog/2015/08/24/xgboost_and_dss.html | |
| from pandas.core.categorical import Categorical | |
| from scipy.sparse import csr_matrix | |
| import numpy as np | |
| def sparse_dummies(categorical_values): | |
| categories = Categorical.from_array(categorical_values) | |
| N = len(categorical_values) | |
| row_numbers = np.arange(N, dtype=np.int) | |
| ones = np.ones((N,)) |
| from scipy import exp, log | |
| from scipy.special import gammaln | |
| def prob_unique(N, r): | |
| """ If you have a set of N things to choose from, and take r samples, | |
| the probability that all r samples are unique. | |
| http://www.johndcook.com/blog/2016/01/30/general-birthday-problem | |
| """ | |
| return exp( gammaln(N+1) - gammaln(N-r+1) - r*log(N) ) |
##VGG16 model for Keras
This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.
It has been obtained by directly converting the Caffe model provived by the authors.
Details about the network architecture can be found in the following arXiv paper:
Very Deep Convolutional Networks for Large-Scale Image Recognition
K. Simonyan, A. Zisserman
| tag = 'h1' | |
| text 'This is a headline' | |
| sentence = '<{0}>{1}</{0}>'.format(tag, text) | |
| person = {'name': 'Jenn', 'age': 23} | |
| sentence = 'My name is {0[name]} and I am {0[age]} years old.'.format(person) | |
| # can do the same for attributes, e.g., {0.name}, or list {0[0]} | |
| # You can just unpack a dictionary! | |
| sentence = 'My name is {name} and I am {age} years old.'.format(**person) |
| def removeLink(content): | |
| urls = re.findall('http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', content) | |
| for i in range(0, len(urls)): | |
| content = content.replace(urls[i], '') | |
| return content |