jakevdp

# Author: Jake VanderPlas
# LICENSE: MIT

from __future__ import division
import numpy as np


def convolution_matrix(x, N=None, mode='full'):
    """Compute the Convolution Matrix

gati

from sklearn.cross_validation import train_test_split
from keras.preprocessing import sequence, text
from keras.models import Sequential
from keras.layers import (Dense, Dropout, Activation, Embedding, LSTM,
                            Convolution1D, MaxPooling1D)

# Embedding
max_features = 20000
maxlen = 100
embedding_size = 32

kayousterhout

Generating Flame Graphs for Apache Spark

Flame graphs are a nifty debugging tool to determine where CPU time is being spent. Using the Java Flight recorder, you can do this for Java processes without adding significant runtime overhead.

When are flame graphs useful?

Shivaram Venkataraman and I have found these flame recordings to be useful for diagnosing coarse-grained performance problems. We started using them at the suggestion of Josh Rosen, who quickly made one for the Spark scheduler when we were talking to him about why the scheduler caps out at a throughput of a few thousand tasks per second. Josh generated a graph similar to the one below, which illustrates that a significant amount of time is spent in serialization (if you click in the top right hand corner and search for "serialize", you can see that 78.6% of the sampled CPU time was spent in serialization). We used this insight to spee

nzw0301

*2vec papers

1. act2vec, trace2vec, log2vec, model2vec https://link.springer.com/chapter/10.1007/978-3-319-98648-7_18
2. apk2vec https://arxiv.org/abs/1809.05693
3. app2vec http://paul.rutgers.edu/~qma/research/ma_app2vec.pdf
4. ast2vec https://arxiv.org/abs/2103.11614
5. attribute2vec https://arxiv.org/abs/2004.01375
6. author2vec http://dl.acm.org/citation.cfm?id=2889382
7. baller2vec https://arxiv.org/abs/2102.03291
8. bb2vec https://arxiv.org/abs/1809.09621

twiecki

glamp

import pandas as pd
# http://blog.yhathq.com/static/misc/data/WineKMC.xlsx
df_offers = pd.read_excel("./WineKMC.xlsx", sheetname=0)
df_offers.columns = ["offer_id", "campaign", "varietal", "min_qty", "discount", "origin", "past_peak"]
df_offers.head()

df_transactions = pd.read_excel("./WineKMC.xlsx", sheetname=1)
df_transactions.columns = ["customer_name", "offer_id"]
df_transactions['n'] = 1
df_transactions.head()

andershammar

%pyspark

import matplotlib.pyplot as plt; plt.rcdefaults()
import numpy as np
import matplotlib.pyplot as plt
import StringIO

def show(p):
    img = StringIO.StringIO()
    p.savefig(img, format='svg')

kastnerkyle

# Authors: Kyle Kastner
# License: BSD 3-clause
import theano.tensor as T
import numpy as np
import theano


class rmsprop(object):
    """
    RMSProp with nesterov momentum and gradient rescaling

karpathy

"""
This is a batched LSTM forward and backward pass
"""
import numpy as np
import code

class LSTM:
  
  @staticmethod
  def init(input_size, hidden_size, fancy_forget_bias_init = 3):

Newmu

import theano
import theano.tensor as T
from theano.sandbox.rng_mrg import MRG_RandomStreams as RandomStreams
from theano.tensor.signal.downsample import max_pool_2d
from theano.tensor.extra_ops import repeat
from theano.sandbox.cuda.dnn import dnn_conv

from time import time
import numpy as np
from matplotlib import pyplot as plt