syhw

from sklearn.datasets import fetch_20newsgroups, load_digits
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cross_validation import train_test_split
import numpy as np
from sklearn.naive_bayes import MultinomialNB, BernoulliNB
from sklearn.linear_model import LogisticRegression, SGDClassifier
from sklearn import metrics

newsgroups_train = fetch_20newsgroups(subset='train')
vectorizer = TfidfVectorizer(encoding='latin-1', max_features=10000)

syhw

"""
A deep neural network with or w/o dropout in one file.
"""

import numpy
import theano
import sys
import math
from theano import tensor as T
from theano import shared

bsweger

Useful Pandas Snippets

A personal diary of DataFrame munging over the years.

Data Types and Conversion

Convert Series datatype to numeric (will error if column has non-numeric values)
(h/t @makmanalp)

syhw

"""
A deep neural network with or w/o dropout in one file.

License: Do What The Fuck You Want to Public License http://www.wtfpl.net/
"""

import numpy, theano, sys, math
from theano import tensor as T
from theano import shared
from theano.tensor.shared_randomstreams import RandomStreams

roycoding

Beating the Forest Cover Type Prediction benchmark

Day 4 of the Beat 5 Kaggle Benchmarks in 5 Days challenge

For the Forest Cover Type Prediction competition on Kaggle, the goal is to predict the predominant type of trees in a given section of forest. The score is based on average classification accuracy for the 7 different tree cover classes.

To beat the all fir/spruce benchmark I obviously tried a random forest. Using the default settings of scikit-learn's RandomForestClassifier, I was able to beat the benchmark with an accuracy score of 0.72718 on the competition leaderboard. By using 100 estimators (versus the default of 10), I was able to raise that accuracy score up to 0.75455.

Random Forest Cover Types

Using pandas I loaded the train and test data sets into Python.

larsmans

import numpy as np
#from scipy.special import chdtrc
from scipy.sparse import spdiags

from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.preprocessing import LabelBinarizer


def _chisquare(f_obs, f_exp, reduce):
    """Replacement for scipy.stats.chisquare with custom reduction.

ebressert

import seaborn as sns
from scipy.optimize import curve_fit

# Function for linear fit
def func(x, a, b):
    return a + b * x

# Seaborn conveniently provides the data for
# Anscombe's quartet.
df = sns.load_dataset("anscombe")

kastnerkyle

# Alec Radford, Indico, Kyle Kastner
# License: MIT
"""
Convolutional VAE in a single file.
Bringing in code from IndicoDataSolutions and Alec Radford (NewMu)
Additionally converted to use default conv2d interface instead of explicit cuDNN
"""
import theano
import theano.tensor as T
from theano.compat.python2x import OrderedDict

tokestermw

"""
preprocess-twitter.py

python preprocess-twitter.py "Some random text with #hashtags, @mentions and http://t.co/kdjfkdjf (links). :)"

Script for preprocessing tweets by Romain Paulus
with small modifications by Jeffrey Pennington
with translation to Python by Motoki Wu

Translation of Ruby script to create features for GloVe vectors for Twitter data.

ebenolson

from lasagne.layers import Layer

class HighwayLayer(Layer):
    def __init__(self, incoming, layer_class, gate_nonlinearity=None,
                 **kwargs):
        super(HighwayLayer, self).__init__(incoming)

        self.H_layer = layer_class(incoming, **kwargs)
        
        if gate_nonlinearity: