fogside

fogside

DeepNLP

0. Intro

   • backprop,
   • theano,
   • mnist classification;

1. Embeddings

   • Text classification: bag of words, TF-IDF

• NLTK: lemmatization, stemming;

fogside

#include <iostream>
#include <algorithm>
#include <stack>
#include <stdexcept>
#include <map>
#include <sstream>
#include <utility>
#include <climits>

using namespace std;

fogside

import os

src_path = '/Users/fogside/Desktop/all_photos/Camera/'
dst_path = '/Users/fogside/Desktop/all_photos/'

###############################################################################################
##### Creating folders like <year-month> in dst_path     ######################################
##### and moving photos from all folders in the src_path ######################################
##### to the corresponding folder <year-month>           ######################################
##### filenames must be like:                            ######################################

fogside

fogside

## Задание 1 -- нужно было просто сделать только одно матричное умножение в имплементации ячейки lstm:

in_mtx = tf.Variable(tf.truncated_normal([vocabulary_size, num_nodes*4], -0.1, 0.1))
out_mtx = tf.Variable(tf.truncated_normal([num_nodes, num_nodes*4], -0.1, 0.1))
b_vec = tf.Variable(tf.zeros([1, num_nodes*4]))

# Variables saving state across unrollings.
saved_output = tf.Variable(tf.zeros([batch_size, num_nodes]), trainable=False)
saved_state = tf.Variable(tf.zeros([batch_size, num_nodes]), trainable=False)

fogside

from itertools import compress
data_index = 0

def generate_batch_cbow(batch_size, num_skips, skip_window):
    '''
    Batch generator for CBOW (Continuous Bag of Words)
    batch should be a shape of (batch_size, num_skips)
    Parameters
    ----------
    batch_size: number of words in each mini-batch

fogside

#!/usr/local/bin/python
# -*- coding: utf-8 -*-

"""  
Summer School problem.
usage:
http letnyayashkola.org/api/v1.0/workshop-programs/ | ./script.py

"""

fogside

import numpy as np
import math
from scipy import stats
from sklearn.neighbors import KDTree
import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning) 
from sklearn.metrics import confusion_matrix
import math