Python Archives

Tag Archive for: Python

On the difficulty of language: prerequisites for NLP with deep learning

January 27, 2021/in Artificial Intelligence, Big Data, Data Mining, Data Science, Data Science Hack, Deep Learning, Machine Learning, Main Category, Natural Language Processing, Python, TensorFlow, Text Mining/by Yasuto Tamura

This is the first article of my article series “Instructions on Transformer for people outside NLP field, but with examples of NLP.”

1 Preface

This section is virtually just my essay on language. You can skip this if you want to get down on more technical topic.

As I do not study in natural language processing (NLP) field, I would not be able to provide that deep insight into this fast changing deep leaning field throughout my article series. However at least I do understand language is a difficult and profound field, not only in engineering but also in many other study fields. Some people might be feeling that technologies are eliminating languages, or one’s motivations to understand other cultures. First of all, I would like you to keep it in mind that I am not a geek who is trying to turn this multilingual world into a homogeneous one and rebuild Tower of Babel, with deep learning. I would say I am more keen on social or anthropological sides of language.

I think you would think more about languages if you have mastered at least one foreign language. As my mother tongue is Japanese, which is totally different from many other Western languages in terms of characters and ambiguity, I understand translating is not what learning a language is all about. Each language has unique characteristics, and I believe they more or less influence one’s personalities. For example, many Western languages make the verb, I mean the conclusion, of sentences clear in the beginning part of the sentences. That is also true of Chinese, I heard. However in Japanese, the conclusion comes at the end, so that is likely to give an impression that Japanese people are being obscure or indecisive. Also, Japanese sentences usually omit their subjects. In German as well, the conclusion of a sentences tend to come at the end, but I am almost 100% sure that no Japanese people would feel German people make things unclear. I think that comes from the structures of German language, which tends to make the number, verb, relations of words crystal clear.

Source: https://twitter.com/nakamurakihiro

Let’s take an example to see how obscure Japanese is. A Japanese sentence 「頭が赤い魚を食べる猫」can be interpreted in five ways, depending on where you put emphases on.

Common sense tells you that the sentence is likely to mean the first two cases, but I am sure they can mean those five possibilities. There might be similarly obscure sentences in other languages, but I bet few languages can be as obscure as Japanese. Also as you can see from the last two sentences, you can omit subjects in Japanese. This rule is nothing exceptional. Japanese people usually don’t use subjects in normal conversations. And when you read classical Japanese, which Japanese high school students have to do just like Western students learn some of classical Latin, the writings omit subjects much more frequently.

*However interestingly we have rich vocabulary of subjects. The subject “I” can be translated to 「私」、「僕」、「俺」、「自分」、「うち」etc, depending on your personality, who you are talking to, and the time when it is written in.

I believe one can see the world only in the framework of their language, and it seems one’s personality changes depending on the language they use. I am not sure whether the language originally determines how they think, or how they think forms the language. But at least I would like you to keep it in mind that if you translate a conversation, for example a random conversation at a bar in Berlin, into Japanese, that would linguistically sound Japanese, but not anthropologically. Imagine that such kind of random conversation in Berlin or something is like playing a catch, I mean throwing a ball named “your opinion.” On the other hand, normal conversations of Japanese people are in stead more of, I would say, “resonance” of several tuning forks. They do their bests to show that they are listening to each other, by excessively nodding or just repeating “Really?”, but usually it seems hardly any constructive dialogues have been made.

*I sometimes feel you do not even need deep learning to simulate most of such Japanese conversations. Several-line Python codes would be enough.

My point is, this article series is mainly going to cover only a few techniques of NLP in deep learning field: sequence to sequence model (seq2seq model) , and especially Transformer. They are, at least for now, just mathematical models and mappings of a small part of this profound field of language (as far as I can cover in this article series). But still, examples of language would definitely help you understand Transformer model in the long run.

2 Tokens and word embedding

*Throughout my article series, “words” just means the normal words you use in daily life. “Tokens” means more general unit of NLP tasks. For example the word “Transformer” might be denoted as a single token “Transformer,” or maybe as a combination of two tokens “Trans” and “former.”

One challenging part of handling language data is its encodings. If you started learning programming in a language other than English, you would have encountered some troubles of using keyboards with different arrangements or with characters. Some comments on your codes in your native languages are sometimes not readable on some software. You can easily get away with that by using only English, but when it comes to NLP you have to deal with this difficulty seriously. How to encode characters in each language should be a first obstacle of NLP. In this article we are going to rely on a library named BPEmb, which provides word embedding in various languages, and you do not have to care so much about encodings in languages all over the world with this library.

In the first section, you might have noticed that Japanese sentence is not separated with spaces like Western languages. This is also true of Chinese language, and that means we need additional tasks of separating those sentences at least into proper chunks of words. This is not only a matter of engineering, but also of some linguistic fields. Also I think many people are not so conscious of how sentences in their native languages are grammatically separated.

The next point is, unlike other scientific data, such as temperature, velocity, voltage, or air pressure, language itself is not measured as numerical data. Thus in order to process language, including English, you first have to map language to certain numerical data, and after some processes you need to conversely map the output numerical data into language data. This section is going to be mainly about one-hot encoding and word embedding, the ways to convert word/token into numerical data. You might already have heard about this

You might have learnt about word embedding to some extent, but I hope you could get richer insight into this topic through this article.

2.1 One-hot encoding

One-hot encoding would be the most straightforward way to encode words/tokens. Assume that you have a dictionary whose size is $|\mathcal{V}|$ , and it includes words from “a”, “ablation”, “actually” to “zombie”, “?”, “!”

In a mathematical manner, in order to choose a word out of those $|\mathcal{V}|$ words, all you need is a $|\mathcal{V}|$ dimensional vector, one of whose elements is $1$ , and the others are $0$ . When you want to choose the No. i word, which is “indeed” in the example below, its corresponding one-hot vector is $\boldsymbol{v} = (0, \dots, 1, \dots, 0 )$ , where only the No. i element is $1$ . One-hot encoding is also easy to understand, and that’s all. It is easy to imagine that people have already come up with more complicated and better way to encoder words. And one major way to do that is word embedding.

2.2 Word embedding

Source: Francois Chollet, Deep Learning with Python,(2018), Manning

Actually word embedding is related to one-hot encoding, and if you understand how to train a simple neural network, for example densely connected layers, you would understand word embedding easily. The key idea of word embedding is denoting each token with a $D$ dimensional vector, whose dimension is fewer than the vocabulary size $|\mathcal{V}|$ . The elements of the resulting word embedding vector are real values, I mean not only 0 or 1. Obviously you can encode much richer variety of tokens with such vectors. The figure at the left side is from “Deep Learning with Python” by François Chollet, and I think this is an almost perfect and simple explanation of the comparison of one-hot encoding and word embedding. But the problem is how to get such convenient vectors. The answer is very simple: you have only to train a network whose inputs are one-hot vector of the vocabulary.

The figure below is a simplified model of word embedding of a certain word. When the word is input into a neural network, only the corresponding element of the one-hot vector is 1, and that virtually means the very first input layer is composed of one neuron whose value is 1. And the only one neuron propagates to the next D dimensional embedding layer. These weights are the very values which most other study materials call “an embedding vector.”

When you input each word into a certain network, for example RNN or Transformer, you map the input one-hot vector into the embedding layer/vector. The examples in the figure are how inputs are made when the input sentences are “You’ve got the touch” and “You’ve got the power.” Assume that you have a dictionary of one-hot encoding, whose vocabulary is {“the”, “You’ve”, “Walberg”, “touch”, “power”, “Nights”, “got”, “Mark”, “Boogie”}, and the dimension of word embeding is 6. In this case $|\mathcal{V}| = 9, D=6$ . When the inputs are “You’ve got the touch” or “You’ve got the power” , you put the one-hot vector corresponding to “You’ve”, “got”, “the”, “touch” or “You’ve”, “got”, “the”, “power” sequentially every time step $t$ .

In order to get word embedding of certain vocabulary, you just need to train the network. We know that the words “actually” and “indeed” are used in similar ways in writings. Thus when we propagate those words into the embedding layer, we can expect that those embedding layers are similar. This is how we can mathematically get effective word embedding of certain vocabulary.

More interestingly, if word embedding is properly trained, you can mathematically “calculate” words. For example, $\boldsymbol{v}_{king} - \boldsymbol{v}_{man} + \boldsymbol{v}_{woman} \approx \boldsymbol{v}_{queen}$ , $\boldsymbol{v}_{Japan} - \boldsymbol{v}_{Tokyo} + \boldsymbol{v}_{Vietnam} \approx \boldsymbol{v}_{Hanoi}$ .

*I have tried to demonstrate this type of calculation on several word embedding, but none of them seem to work well. At least you should keep it in mind that word embedding learns complicated linear relations between words.

I should explain word embedding techniques such as word2vec in detail, but the main focus of this article is not NLP, so the points I have mentioned are enough to understand Transformer model with NLP examples in the upcoming articles.

3 Language model

Language models is one of the most straightforward, but crucial ideas in NLP. This is also a big topic, so this article is going to cover only basic points. Language model is a mathematical model of the probabilities of which words to come next, given a context. For example if you have a sentence “In the lecture, he opened a _.”, a language model predicts what comes at the part “_.” It is obvious that this is contextual. If you are talking about general university students, “_” would be “textbook,” but if you are talking about Japanese universities, especially in liberal art department, “_” would be more likely to be “smartphone. I think most of you use this language model everyday. When you type in something on your computer or smartphone, you would constantly see text predictions, or they might even correct your spelling or grammatical errors. This is language modelling. You can make language models in several ways, such as n-gram and neural language models, but in this article I can explain only general formulations for such models.

*I am not sure which algorithm is used in which services. That must be too fast changing and competitive for me to catch up.

As I mentioned in the first article series on RNN, a sentence is usually processed as sequence data in NLP. One single sentence is denoted as $\boldsymbol{X} = (\boldsymbol{x}^{(1)}, \dots, \boldsymbol{x}^{(\tau)})$ , a list of vectors. The vectors are usually embedding vectors, and the $(t)$ is the index of the order of tokens. For example the sentence “You’ve go the power.” can be expressed as $\boldsymbol{X} = (\boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)}, \boldsymbol{x}^{(3)}, \boldsymbol{x}^{(4)})$ , where $\boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)}, \boldsymbol{x}^{(3)}, \boldsymbol{x}^{(4)}$ denote “You’ve”, “got”, “the”, “power”, “.” respectively. In this case $\tau = 4$ .

In practice a sentence $\boldsymbol{X}$ usually includes two tokens $BOS$ and $EOS$ at the beginning and the end of the sentence. They mean “Beginning Of Sentence” and “End Of Sentence” respectively. Thus in many cases $\boldsymbol{X} = (\boldsymbol{BOS} , \boldsymbol{x}^{(1)}, \dots, \boldsymbol{x}^{(\tau)}, \boldsymbol{EOS} )$ . $\boldsymbol{BOS}$ and $\boldsymbol{EOS}$ are also both vectors, at least in the Tensorflow tutorial.

$P(\boldsymbol{X} =$ $(\boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \dots, \boldsymbol{x}^{(\tau)}, \boldsymbol{EOS})$ is the probability of incidence of the sentence. But it is easy to imagine that it would be very hard to directly calculate how likely the sentence $\boldsymbol{X}$ appears out of all possible sentences. I would rather say it is impossible. Thus instead in NLP we calculate the probability $P(\boldsymbol{X})$ as a product of the probability of incidence or a certain word, given all the words so far. When you’ve got the words $(\boldsymbol{x}^{(1)}, \dots, \boldsymbol{x}^{(t-1})$ so far, the probability of the incidence of $\boldsymbol{x}^{(t)}$ , given the context is $P(\boldsymbol{x}^{(t)}|\boldsymbol{x}^{(1)}, \dots, \boldsymbol{x}^{(t-1)})$ . $P(\boldsymbol{BOS})$ is a probability of the the sentence $\boldsymbol{X}$ being $(\boldsymbol{BOS})$ , and the probability of $\boldsymbol{X}$ being $(\boldsymbol{BOS}, \boldsymbol{x}^{(1)})$ can be decomposed this way: $P(\boldsymbol{BOS}, \boldsymbol{x}^{(1)}) =$ $P(\boldsymbol{x}^{(1)}|\boldsymbol{BOS})P(\boldsymbol{BOS})$ .

Just as well $P(\boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)}) =$ $P(\boldsymbol{x}^{(2)}| \boldsymbol{BOS}, \boldsymbol{x}^{(1)}) P( \boldsymbol{BOS}, \boldsymbol{x}^{(1)})=$ $P(\boldsymbol{x}^{(2)}| \boldsymbol{BOS}, \boldsymbol{x}^{(1)}) P(\boldsymbol{x}^{(1)}| \boldsymbol{BOS}) P( \boldsymbol{BOS})$ .

Hence, the general probability of incidence of a sentence $\boldsymbol{X}$ is $P(\boldsymbol{X})=P(\boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)}, \dots, \boldsymbol{x}^{(\tau -1)}, \boldsymbol{x}^{(\tau)}, \boldsymbol{EOS}) =$ $P(\boldsymbol{EOS}| \boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \dots, \boldsymbol{x}^{(\tau)})$ $P(\boldsymbol{x}^{(\tau)}| \boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \dots, \boldsymbol{x}^{(\tau - 1)})$ $\cdots$ $P(\boldsymbol{x}^{(2)}| \boldsymbol{BOS}, \boldsymbol{x}^{(1)})$ $P(\boldsymbol{x}^{(1)}| \boldsymbol{BOS})$ $P(\boldsymbol{BOS})$ .

Let $\boldsymbol{x}^{(0)}$ be $\boldsymbol{BOS}$ and $\boldsymbol{x}^{(\tau + 1)}$ be $\boldsymbol{EOS}$ . Plus, let $P(\boldsymbol{x}^{(t+1)}|\boldsymbol{X}_{[0, t]})$ be $P(\boldsymbol{x}^{(t+1)}|\boldsymbol{x}^{(0)}, \dots, \boldsymbol{x}^{(t)})$ , then $P(\boldsymbol{X}) = P(\boldsymbol{x}^{(0)})\prod_{t=0}^{\tau}{P(\boldsymbol{x}^{(t+1)}|\boldsymbol{X}_{[0, t]})}$ . Language models calculate which words to come sequentially in this way.

Here’s a question: how would you evaluate a language model?

I would say the answer is, when the language model generates words, the more confident the language model is, the better the language model is. Given a context, when the distribution of the next word is concentrated on a certain word, we can say the language model is confident about which word to come next, given the context.

*For some people, it would be more understandable to call this “entropy.”

Let’s take the vocabulary {“the”, “You’ve”, “Walberg”, “touch”, “power”, “Nights”, “got”, “Mark”, “Boogie”} as an example. Assume that $P(\boldsymbol{X}) =$ $P(\boldsymbol{BOS}, \boldsymbol{You've}, \boldsymbol{got}, \boldsymbol{the}, \boldsymbol{touch}, \boldsymbol{EOS}) =$ $P(\boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)}, \boldsymbol{x}^{(3)}, \boldsymbol{x}^{(4)}, \boldsymbol{EOS})=$ $P(\boldsymbol{x}^{(0)})\prod_{t=0}^{4}{P(\boldsymbol{x}^{(t+1)}|\boldsymbol{X}_{[0, t]})}$ . Given a context $(\boldsymbol{BOS}, \boldsymbol{x}^{(1)})$ , the probability of incidence of $\boldsymbol{x}^{(2)}$ is $P(\boldsymbol{x}^{2}|\boldsymbol{BOS}, \boldsymbol{x}^{(1)})$ . In the figure below, the distribution at the left side is less confident because probabilities do not spread widely, on the other hand the one at the right side is more confident that next word is “got” because the distribution concentrates on “got”.

*You have to keep it in mind that the sum of all possible probability $P(\boldsymbol{x}^{(2)} | \boldsymbol{BOS}, \boldsymbol{x}^{(1)})$ is $1$ , that is, $P(\boldsymbol{the}| \boldsymbol{BOS}, \boldsymbol{x}^{(1)}) +$ $P(\boldsymbol{You've}| \boldsymbol{BOS}, \boldsymbol{x}^{(1)}) + \cdots$ $+ P(\boldsymbol{Boogie}| \boldsymbol{BOS}, \boldsymbol{x}^{(1)}) = 1$ .

While the language model generating the sentence “BOS You’ve got the touch EOS”, it is better if the language model keeps being confident. If it is confident, $P(\boldsymbol{X})=$ $P(\boldsymbol{BOS})$ $P(\boldsymbol{x}^{(1)}|\boldsymbol{BOS}}P(\boldsymbol{x}^{(3)}|\boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)})$ $P(\boldsymbol{x}^{(4)}|\boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)}, \boldsymbol{x}^{(3)})$ $P(\boldsymbol{EOS}|\boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)}, \boldsymbol{x}^{(3)}, \boldsymbol{x}^{(4)})}$ gets higher. Thus $(-1) \{ log_{b}{P(\boldsymbol{BOS})} +$ $log_{b}{P(\boldsymbol{x}^{(1)}|\boldsymbol{BOS}}) +$ $log_{b}{P(\boldsymbol{x}^{(3)}|\boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)})} +$ $log_{b}{P(\boldsymbol{x}^{(4)}|\boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)}, \boldsymbol{x}^{(3)})} +$ $log_{b}{P(\boldsymbol{EOS}|\boldsymbol{BOS}, \boldsymbol{x}^{(1)}, \boldsymbol{x}^{(2)}, \boldsymbol{x}^{(3)}, \boldsymbol{x}^{(4)})} \}$ gets lower, where usually $b=2$ or $b=e$ .

This is how to measure how confident language models are, and the indicator of the confidence is called perplexity. Assume that you have a data set for evaluation $\mathcal{D} = (\boldsymbol{X}_1, \dots, \boldsymbol{X}_n, \dots, \boldsymbol{X}_{|\mathcal{D}|})$ , which is composed of $|\mathcal{D}|$ sentences in total. Each sentence $\boldsymbol{X}_n =$ $(\boldsymbol{x}^{(0)})\prod_{t=0}^{\tau ^{(n)}}{P(\boldsymbol{x}_{n}^{(t+1)}|\boldsymbol{X}_{n, [0, t]})}$ has $\tau^{(n)}$ tokens in total excluding $\boldsymbol{BOS}, \boldsymbol{EOS}$ . And let $|\mathcal{V}|$ be the size of the vocabulary of the language model. Then the perplexity of the language model is $b^z$ , where $z = \frac{-1}{|\mathcal{V}|}\sum_{n=1}^{|\mathcal{D}|}{\sum_{t=0}^{\tau ^{(n)}}{log_{b}P(\boldsymbol{x}_{n}^{(t+1)}|\boldsymbol{X}_{n, [0, t]})}$ . The $b$ is usually $2$ or $e$ .

For example, assume that $\mathcal{V}$ is vocabulary {“the”, “You’ve”, “Walberg”, “touch”, “power”, “Nights”, “got”, “Mark”, “Boogie”}. Also assume that the evaluation data set for perplexity of a language model is $\mathcal{D} = (\boldsymbol{X}_1, \boldsymbol{X}_2)$ , where $\boldsymbol{X_1} =(\boldsymbol{You've}, \boldsymbol{got}, \boldsymbol{the}, \boldsymbol{touch})$ $\boldsymbol{X_2} = (\boldsymbol{You've}, \boldsymbol{got}, \boldsymbol{the }, \boldsymbol{power})$ . In this case $|\mathcal{V}|=9,$ $|\mathcal{D}|=2$ . I have already showed you how to calculate the perplexity of the sentence “You’ve got the touch.” above. You just need to do a similar thing on another sentence “You’ve got the power”, and then you can get the perplexity of the language model.

*If the network is not properly trained, it would also be confident of generating wrong outputs. However, such network still would give high perplexity because it is “confident” at any rate. I’m sorry I don’t know how to tackle the problem. Please let me put this aside, and let’s get down on Transformer model soon.

Appendix

Let’s see how word embedding is implemented with a very simple example in the official Tensorflow tutorial. It is a simple binary classification task on IMDb Dataset. The dataset is composed to comments on movies by movie critics, and you have only to classify if the commentary is positive or negative about the movie. For example when you get you get an input “To be honest, Michael Bay is a terrible as an action film maker. You cannot understand what is going on during combat scenes, and his movies rely too much on advertisements. I got a headache when Mark Walberg used a Chinese cridit card in Texas. However he is very competent when it comes to humorous scenes. He is very talented as a comedy director, and I have to admit I laughed a lot.“, the neural netowork has to judge whether the statement is positive or negative.

This networks just takes an average of input embedding vectors and regress it into a one dimensional value from 0 to 1. The shape of embedding layer is (8185, 16). Weights of neural netowrks are usually implemented as matrices, and you can see that each row of the matrix corresponds to emmbedding vector of each token.

*It is easy to imagine that this technique is problematic. This network virtually taking a mean of input embedding vectors. That could mean if the input sentence includes relatively many tokens with negative meanings, it is inclined to be classified as negative. But for example, if the sentence is “This masterpiece is a dark comedy by Charlie Chaplin which depicted stupidity of the evil tyrant gaining power in the time. It thoroughly mocked Germany in the time as an absurd group of fanatics, but such propaganda could have never been made until ‘Casablanca.'” , this can be classified as negative, because only the part “masterpiece” is positive as a token, and there are much more words with negative meanings themselves.

The official Tensorflow tutorial provides visualization of word embedding with Embedding Projector, but I would like you to take more control over the data by yourself. Please just copy and paste the codes below, installing necessary libraries. You would get a map of vocabulary used in the text classification task. It seems you cannot find clear tendency of the clusters of the tokens. You can try other dimension reduction methods to get maps of the vocabulary by for example using Scikit Learn.

import tensorflow as tf

from tensorflow import keras

from tensorflow.keras import layers

import tensorflow_datasets as tfds

tfds.disable_progress_bar()

(train_data, test_data), info = tfds.load(

'imdb_reviews/subwords8k',

split = (tfds.Split.TRAIN, tfds.Split.TEST),

with_info=True, as_supervised=True)

train_batches = train_data.shuffle(1000).padded_batch(10)

test_batches = test_data.shuffle(1000).padded_batch(10)

embedding_dim=16

encoder = info.features['text'].encoder

model = keras.Sequential([

layers.Embedding(encoder.vocab_size, embedding_dim),

layers.GlobalAveragePooling1D(),

layers.Dense(16, activation='relu'),

layers.Dense(1)

])

print("\n\nThe size of the vocabulary generated from IMDb Dataset is " + str(encoder.vocab_size) + '\n\n')

model.summary()

model.compile(optimizer='adam',

loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),

metrics=['accuracy'])

history = model.fit(

train_batches,

epochs=10,

validation_data=test_batches, validation_steps=20)

word_embedding_vectors = model.layers[0].get_weights()[0]

print("\n\nThe shape of the trained weigths of the embedding layer is " + str(word_embedding_vectors.shape) + '\n\n')

from sklearn.manifold import TSNE

X_reduced = TSNE(n_components = 2, init='pca', random_state=0).fit_transform(word_embedding_vectors)

import numpy as np

embedding_dict = zip(encoder.subwords, np.arange(len(encoder.subwords)))

embedding_dict = dict(embedding_dict)

import matplotlib.pyplot as plt

plt.figure(figsize=(60, 45))

plt.scatter(X_reduced[:, 0], X_reduced[:, 1])

for i in range(0, len(encoder.subwords), 5):

plt.text(X_reduced[i, 0], X_reduced[i, 1], encoder.subwords[i], fontsize=20, color='red')

plt.title("The map of vocabulary of IMDb Dataset mapped to a 2 dimensional space by t-SNE", fontsize=60)

#plt.savefig('imdb_tsne_map.png')

plt.show()

[References]

[1] “Word embeddings” Tensorflow Core
https://www.tensorflow.org/tutorials/text/word_embeddings

[2]Tsuboi Yuuta, Unno Yuuya, Suzuki Jun, “Machine Learning Professional Series: Natural Language Processing with Deep Learning,” (2017), pp. 43-64, 72-85, 91-94
坪井祐太、海野裕也、鈴木潤著, 「機械学習プロフェッショナルシリーズ深層学習による自然言語処理」, (2017), pp. 43-64, 72-85, 191-193

[3]”Stanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 8 – Translation, Seq2Seq, Attention”, stanfordonline, (2019)
https://www.youtube.com/watch?v=XXtpJxZBa2c

[4] Francois Chollet, Deep Learning with Python,(2018), Manning , pp. 178-185

[5]”2.2. Manifold learning,” scikit-learn
https://scikit-learn.org/stable/modules/manifold.html

* I make study materials on machine learning, sponsored by DATANOMIQ. I do my best to make my content as straightforward but as precise as possible. I include all of my reference sources. If you notice any mistakes in my materials, including grammatical errors, please let me know (email: yasuto.tamura@datanomiq.de). And if you have any advice for making my materials more understandable to learners, I would appreciate hearing it.

Top 10 Python Libraries Of All Time

December 4, 2020/in Data Science Hack, Insights, Python, Tool Introduction/by Harikrishna Kundariya

Python is a very popular and renowned language that has replaced several programming languages in the market. Its amazing collection of libraries makes it a convenient programming language for developers.

Python is an ocean of libraries serving an ample number of purposes and as a developer; you must possess sound knowledge of the 10 libraries. One needs to familiarize themselves with the libraries to go on and work on different projects. For the data scientist, it has been a charmer now.

Here today, for you this is a curated list of 10 Python libraries that can help you along with its significant features, when to use them, and also the benefits.

10 Best Python Libraries of All Times

Pandas: Pandas is an open-source library that offers instant high performance, data analysis, and simple data structures. When can you use it? It can be used for data munging and wrangling. If one is looking for quick data visuals, aggregation, manipulation, and reading, then this library is suitable. You can impute the missing data files, plot the data, and make edits in the data column. Moreover, for renaming and merging, this tool can do wonders. It is a foundation library, and a data scientist should have in-depth knowledge about Pandas before any other library knowledge.

TensorFlow: TensorFlow is developed by Google in collaboration with the Brain Team. Using this tool, you can instantly visualize any part of the graphical representation. It comes with modularity and offers high flexibility in its operations. This library is ideal for running and operating in large scale systems. So, as long as you have good internet connectivity, you can use it because it is an open-source platform. What is the beauty of this library? It comes with an unending list of applications associated with it.

NumPy: NumPy is the most popular Python library used by developers. It is used by various libraries for conducting easy operations. What is the beauty of NumPy? Array Interface is the beauty of NumPy and it is always a highlighted feature. NumPy is interactive and very simple to use. It can instantly solve complicated mathematical problems. With this, you need not worry about daunting phases of coding and offering open-source contributions. This interface is widely used for expressing raw streams, sound waves, and other images. If you are looking to implement this into machine learning, you must possess in-depth knowledge about NumPy.

Keras: Are you looking for a cool Python library? Well, Keras is the coolest machine learning python library. It runs smoothly on both CPU and GPU. Do you want to know where Keras is used? It is used in popular applications like Uber, Swiggy, Netflix, Square, and Yelp. Keras easily supports the fully connected, pooling, convolution, and recurrent neural networks. For any innovative research, it does fine because it is expressive and flexible. Keras is completely based on a framework, which enables easy debugging and exploring. Various large scientific organizations use Keras for innovative research.

Scikit- Learn: If your project deals with complex data, it has to be the Scikit- Learn python library. This Python Machine Learning Library is associated with NumPy and SciPy. After various modifications, one such feather cross-validation is used for enabling more than one metric. It is used for extracting features and data from texts and images. It uses various algorithms to make changes in machine learning. What are its functions? It is used in model selection, classification, clustering, and regression. Various training methods like nearest neighbor and logistics regressions are subjected to minimal modification.

PyTorch: PyTorch is the largest library which conducts various computations and accelerations. Also, it solves complicated application issues that are related to the neural networks. It is completely based on the machine language Torch, which is a free and open-source platform. PyTorch is new but gaining huge popularity and very much a favorite among the developers. Why such popularity? It comes with a hybrid end-user which ensures easy usage and flexibility. For processing natural language applications, this library is used. Do you know what the best part is? It is outperforming and taking the popularity of Tensor Flow in recent times.

MoviePy: The MoviePy is a tool that offers unending functionality related to movies and visuals. It is used for exporting, modifying, and importing various video files. Do you want to add a title to your video or rotate it 90 degrees? Well, MoviePy helps you to do all such tasks related to videos. It is not a tool for manipulating data like Pillow. In any task related to movies and videos in python coding, you can no doubt rely on the functionality of MoviePy. It is designed to conduct all the aspects of a standard task and can get it done instantly. For any common task associated with videos, it has a MoviePy library.

Matplotlib: Matplotlib is no doubt a quintessential python library whose presence can never be forgotten. You can visualize data and create innovative and interesting stories. When can you use it? You can use Matplotlib for embedding different plots into the application as it provides an object-oriented application program interface. Any sort of visualization, be it bar graph, histogram, pie chart, or graphs, Matplotlib can easily depict it. With this library, you can create any type of visualization. Do you want to know what visualizations you can create? You can create a histogram, Bar graph, pie chart, area plot, stem plot, and line plot. It also facilitates the legends, grids, and labels.
Tkinter: Tkinter is a library that can help you create any Python application with the help of a graphical user interface. Tkinter is the most common and easy to use python library for developing apps with GUI. It binds python to the GUI tool kit which can be used in any modern operating system. To create a python GUI, Tkinter is the only best way to start instantly.
Plotly: The Plotly is an essential graph plotting python library for developers. Users can import, copy, paste, export the data that needs to be analyzed and visualized. When can you use it? You can use Plotly to display and create figures and visual images. What is interesting is that it has amazing features for sending data to the various cloud servers.

What are the visual charts prepared with Plotly? You can create line pie, bubble, dot, scatter, and pie. One can also construct financial charts, contours, maps, subplots, carpet, radar, and logs. Do you have anything in your mind which needs to be represented visually? Use Plotly!

Finishing Up

In a nutshell, you have the best python libraries of recent times which contribute hugely to development. If your favorite python library didn’t make it in this list of the top 10 best python libraries, do not take offense.

Python comes with unending library packages, and these 10 are some of its popular and best-used ones. If you are a python developer, these are the best libraries you must have in-depth knowledge of.

Article series: 5 Clean Coding Tips – 5.Put yourself in somebody else’s shoes

April 28, 2020/in Python, Tool Introduction, Tutorial/by Emilia Cheladze

This is the fifth of the article series “5 tips for clean coding” to follow as soon as you’ve made the first steps into your coding career, in this article series. Read the introduction here, to find out why it is important to write clean code if you missed it.

It might be a bit repetitive to bring up how important the readability of the code is, let’s do it anyway. In the majority of the cases you are writing for others, therefore you need to put yourself in their shoes to be able to assess how good the readability of your code is. For you, it all might be obvious because you wrote it. But it doesn’t have to be easy to read for someone else. If you have a colleague or a friend that has a bit of time for you and is willing to give you feedback, that is great. If, however, you don’t have such a person, having a few imaginary friends might be helpful in this case. It might sound crazy, but don’t close this page just yet. Having a set of imaginary personas at your disposal, to review your work with their eyes, can help you a lot. Imagine that your code met one of those guys. What would they say about it? If you work in a team or collaborate with people, you probably don’t have to imagine them. You’ve met them.

The_PEP8_guy – He has years of experience. He is used to seeing the code in a very particular way. He quotes the style guide during lunch. His fingers make the perfect line splitting and indentation without even his thoughts reaching the conscious state. He knows that lowercase_with_underscore is for variables, UPPER_CASE_NAMES are for constants and the CapitalizedWords are for classes. He will be lost if you do it in any different way. His expectations will not meet what you wrote, and he will not understand anything, because he will be too distracted by the messed up visual. Depending on the character he might start either crying or shouting. Read the style guide and follow it. You might be able to please this guy at least a little bit with the automatic tools like pylint.

The_ grieving _widow – Imagine that something happens to you. Let’s say, that you get hit by a bus[i]. You leave behind sadness and the_ grieving_widow to manage your code, your legacy. Will the future generations be able to make use of it or were you the only one who can understand anything you wrote? That is a bit of an extreme situation, ok. Alternatively, imagine, that you go for a 5-week vacation to a silent retreat with a strict no-phone policy (or that is what you tell your colleagues). Will they be able to carry on if they cannot ask you anything about the code? Review your code and the documentation from the perspective of the poor grieving_widow.

The_not_your_domain_guy – He is from the outside of the world you are currently in and he just does not understand your jargon. He doesn’t have to know that in data science a feature, a predictor and an x probably mean the same thing. SNR might shout signal-to-noise ratio at you, it will only snort at him. You might use abbreviations that are obvious to you but not to everyone. If you think that the majority of people can understand, and it helps with the code readability keep the abbreviations but just in case, document/comment them. There might be abbreviations specific to your company and, someone from the outside, a new guy, a consultant will not get them. Put yourself in the shoes of that guy and maybe make your code a bit more democratic wherever possible.

The_foreigner– You might be working in an environment, where every single person speaks the same language you speak, and it happens not to be English. So, you and your colleagues name variables and write the comments in your language. However, unless you work in a team with rules a strict as Athletic Bilbao, there might be a foreigner joining your team in the future. It is hard to argue that English is the lingua franca in programming (and in the world), these days. So, it might be worth putting yourself in the_foreigner’s shoes, while writing your code, to avoid a huge amount of work in the future, that the translation and explanation will require. And even if you are working on your own, you might want to make your code public one day and want as many people as possible to read it.

The_hurry_up_guy – we all know this guy. Sometimes he doesn’t have a body or a face, but we can feel his presence. You might want to write a perfect solution, comment it in the best possible way and maybe add a bit of glitter on top but sometimes you just need to give in and do it his way. And that’s ok too.

References:

[i] https://en.wikipedia.org/wiki/Bus_factor

Article series: 5 Clean Coding Tips – 3. Take Advantage of the Formatting Tools.

April 6, 2020/in Python, Tool Introduction, Tutorial/by Emilia Cheladze

This is the third of the article series “5 tips for clean coding” to follow as soon as you’ve made the first steps into your coding career, in this article series. Read the introduction here, to find out why it is important to write clean code if you missed it.

Unfortunately, no automatic formatting tool will correct the logic in your code, suggest meaningful names of your variables or comment the code for you. Yet. Gmail has lately started suggesting email titles based on email content. AI-powered variable naming can be next, who knows. Anyway, the visual level of the code is much easier to correct and there are tools that will do some of the code formatting on the visual level job for you. Some of them might be already existing in your IDE, you just need to look for them a bit, others need to be installed. One of the most popular formatting tools is pylint[i]. It is worth checking it out and learning to use it in an efficient way.

Beware that as convenient as it may seem to copy and paste your code into a quick online ‘beautifier’ it is not always a good idea. The online tools might store your code. If you are working on something that shouldn’t just freely float in the world wide web, stick to reliable tools like pylint, that will store the data within your working directory.

These tools can become very good friends of yours but also very annoying ones. They will not miss single whitespace and will not keep their mouth shut when your line length jumps from 79 to 80 characters. They will be shouting with an underscoring of some worrying color and/or exclamation marks. You will need to find your way to coexist and retain your sanity. It can be very distracting when you are in a working flow and warnings pop up all the time about formatting details that have nothing to do with what you are trying to solve. Sometimes, it might be better to turn those warnings off while you are in your most concentrated/creative phase of writing and turn them back on while the dust of your genius settles down a little bit. Usually the offer a lot of flexibility, regarding which warnings you want to be ignored and other features. The good thing is, they also teach you what are mistakes that you are making and after some time you will just stop making them in the first place.

References:

[i] https://www.pylint.org/

Article series: 5 Clean Coding Tips – 2. Name Variables in a Meaningful Way

March 27, 2020/in Python, Tool Introduction, Tutorial/by Emilia Cheladze

This is the second of the article series “5 tips for clean coding” to follow as soon as you’ve made the first steps into your coding career, in this article series. Read the introduction here, to find out why it is important to write clean code if you missed it.

When it comes to naming variables, there are a few official rules in the PEP8 style guide. A variable must start with an underscore or a letter and can be followed by a number of underscores or letters or digits. They cannot be reserved words: True, False, or, not, lambda etc. The preferred naming style is lowercase or lowercase_with_underscore. This all refers to variable names on a visual level. However, for readability purposes, the semantic level is as important, or maybe even more so. If it was for python, the variables could be named like this:

b_a327647_3 = DataFrame()

hw_abc7622 = DataFrame()

a10001_kkl = DataFrame()

It wouldn’t make the slightest difference. But again, the code is not only for the interpreter to be read. It is for humans. Other people might need to look at your code to understand what you did, to be able to continue the work that you have already started. In any case, they need to be able to decipher what hides behind the variable names, that you’ve given the objects in your code. They will need to remember what they meant as they reappear in the code. And it might not be easy for them.

Remembering names is not an easy thing to do in all life situations. Let’s consider the following situation. You go to a party, there is a bunch of new people that you meet for the first time. They all have names and you try very hard to remember them all. Imagine how much easier would it be if you could call the new girl who came with John as the_girl_who_came_with_John. How much easier would it be to gossip to your friends about her? ‘Camilla is on the 5^th glass of wine tonight, isn’t she?!.’ ‘Who are you talking about???’ Your friends might ask. ‘The_Girl_who_came_with_John.’ And they will all know. ‘It was nice to meet you girl_who_came_with_john, see you around.’ The good thing is that variables are not really like people. You can be a bit rude to them, they will not mind. You don’t have to force yourself or anyone else to remember an arbitrary name of a variable, that accidentally came to your mind in the moment of creation. Let your colleagues figure out what is what by a meaningful, straightforward description of it.

There is an important tradeoff to be aware of here. The lines of code should not exceed a certain length (79 characters, according to the PEP 8), therefore, it is recommended that you keep your names as short as possible. It is worth to give it a bit of thought about how you can name your variable in the most descriptive way, keeping it as short as possible. Keep in mind, that
the_blond_girl_in_a_dark_blue_dress_who_came_with_John_to_this_party might not be the best choice.

There are a few additional pieces of advice when it comes to naming your variables. First, try to always use pronounceable names. If you’ve ever been to an international party, you will know how much harder to remember is something that you cannot even repeat. Second, you probably have been taught over and over again that whenever you create a loop, you use i and j to denote the iterators.

1 2	for i in m: for j in n:

It is probably engraved deep into the folds in your brain to write for i in…. You need to try and scrape it out of your cortex. Think about what the i stands for, what it really does and name it accordingly. Is i maybe the row_index? Is it a list_element?

1 2	for element in list_of_words: for letter in word:

Additionally, think about when to use a noun and where a verb. Variables usually are things and functions usually do things. So, it might be better to name functions with verb expressions, for example: get_id() or raise_to_power().

Moreover, it is a good practice to name constant numbers in the code. First, because when you name them you explain the meaning of the number. Second, because maybe one day you will have to change that number. If it appears multiple times in your code, you will avoid searching and changing it in every place. PEP 8 states that the constants should be named with UPPER_CASE_NAME. It is also quite common practice to explain the meaning of the constants with an inline comment at the end of the line, where the number appears. However, this approach will increase the line length and will require repeating the comment if the number appears more than one time in the code.

Article series: 5 Clean Coding Tips – 1. Be Consistent

March 13, 2020/in Python, Tool Introduction, Tutorial/by Emilia Cheladze

This is the first of the article series “5 tips for clean coding” to follow as soon as you’ve made the first steps into your coding career, in this article series. Read the introduction here, to find out why it is important to write clean code if you missed it.

Consistency is THE rule to follow if you want to make your code clean and increase readability. Not to make it sound desperate, but honestly, whatever you decide to do when it comes to the coding style, just be consistent. Whether you agree with any standards, formatting styles or don’t even know them, just be consistent. Don’t ever allow inconsistency to sneak into your script or your project. This will only bring confusion, disorientation, chaos and general misery.

The rules for how exactly keep your code clean and organized visually might differ slightly depending on the situation you find yourself in. The PEP 8 rules can be ambiguous in some places and leave room for interpretation. For example, the question, whether you use single or double quotes to denote a string, is open. It is possible, that your work environment already has a standard and you just need to comply with that. No room to show off your highly unique take on it, sorry. However, if you are working on your own and there is no one to roll their eyes looking at your messed-up code, you need to decide for yourself. Once you do, again, be consistent at the level of the script, project, your work in general. Otherwise, it will look messy, patchworky and simply unprofessional.

People famously are quick to ascribe intentionality, even to thermostats[i]. They will assume that the details of how you wrote your code are intentional. They will try to figure out why you are doing one thing in some places and a different thing in other places. If those differences came from you being careless and have no meaning behind them, the reader of your code will waste a lot of time trying to figure it out and end up frustrated. Remember the first few snippets of python code you have ever seen? Maybe you saw some code with double quotes and some with single quotes. You were green, knew nothing and quite possibly thought that they both have different meanings and you spent time trying to figure out why on earth in some places there is a single quote and in other double-quotes.

food=('ham', 'cheese')

fruit = ( "apple" , '''orange''' ,

"berry" )

If those altruistic arguments do not really convince you, let’s see how consistency can serve to your own benefit. First, that outsider, who is looking at your code and is trying very hard to figure out what on Earth is going on, might be you. It might sound crazy, and it is, indeed, quite sad, but most likely, after 6 months of not looking at your code you will no longer remember what you did there if it is not documented well. Documenting in a homogenous way can take some time and some effort. Nevertheless, in general, code gets read many times after it has been written. When in doubt, sacrifice some of your writing time to increase readability and minimize the reading time later. It will pay off in the long run.

Having a set of rules at your disposal can make your work faster. You will avoid arguing with yourself about which option is the best one: mean_income, income_mean or income_avg. You can avoid making loads of small decisions as you write your code by making a set of global rules. In that way, you can allocate your energy and resources into solving the real problem. Not the how-do-I-format-this? one.

It is not necessary that you make all those grand decisions right now. You also don’t have to make them for life, it’s ok to change your mind eventually, so don’t feel overwhelmed. But once you’ve learned this and that, spent a little time coding, have a good long look at your sprouting habits and decide what you are going to do about splitting those lines and stick to it!

References:

[i] https://en.wikipedia.org/wiki/Intentional_stance

Article series: 5 Clean Coding Tips

March 7, 2020/in Main Category, Python, Software Development, Tool Introduction, Tutorial/by Emilia Cheladze

This series of articles will cover 5 clean coding tips to follow as soon as you’ve made the first steps into your coding career, with the example of python.

At the beginning of your adventure with coding, you might find that getting your code to compile without any errors and give you the output that you expect is hard enough. Conforming to any standards and style guides is at the very bottom of your concerns. You might be at the beginning of your career or you might have a lot of domain experience but not that much in coding. Or maybe until now you worked mostly on your own and never had to make your code available for others to work with it. In any case, it is worth acknowledging how crucial it is to write your code in a concise, readable and understandable way, and how much benefits it will eventually bring you.

The first thing to realize is that the whole clean coding concept has been developed for people, your fellow travelers, not for the computers. The compiler doesn’t care how you name your variables, how you split your lines or if everything is aligned in a pretty way. You could even write your code as a one gigantic, few-meters-long line, giving the interpreter just a signal – a semicolon, that the line should be split, and it will execute it perfectly.

However, it is likely that, the deeper you are into your career, the more people will have to read, understand and modify the code that you wrote. You will write code to communicate certain ideas and solutions with other people. Therefore, you need to be sure, that what you want to communicate is understandable, easy and quick to read. The coding best practice is to always code in a clean way, treating the code itself and not just the output as the result of your work.

There usually are fixed rules and standards regarding code readability. For python, it is the PEP 8[i]. Some companies elaborate on those standards where the PEP 8 is a bit vague or leaves room for interpretation. The exact formatting styles might differ at Facebook, Google[ii] or at the company you happen to work for. But before you get lost in the art of a perfect line splitting, brackets alignment technique, or the hopeless tabs or spaces battle, have a look at the 5 tips in the upcoming articles in this series. They are universal and might help you make your code, less of a chaotic mess and more of blissful delight.

List of articles in this series:

Be consistent
Name variables in a meaningful way
Take advantage of the formatting tools
Stop commenting the obvious
Put yourself in somebody else’s shoes

References:

[i] https://www.python.org/dev/peps/pep-0008/
[ii] http://google.github.io/styleguide/pyguide.html

Python vs R: Which Language to Choose for Deep Learning?

February 18, 2020/in Data Mining, Data Science, Insights, Python, R Statistics/by Deep Moteria

Data science is increasingly becoming essential for every business to operate efficiently in this modern world. This influences the processes composed together to obtain the required outputs for clients. While machine learning and deep learning sit at the core of data science, the concepts of deep learning become essential to understand as it can help increase the accuracy of final outputs. And when it comes to data science, R and Python are the most popular programming languages used to instruct the machines.

Python and R: Primary Languages Used for Deep Learning

Deep learning and machine learning differentiate based on the input data type they use. While machine learning depends upon the structured data, deep learning uses neural networks to store and process the data during the learning. Deep learning can be described as the subset of machine learning, where the data to be processed is defined in another structure than a normal one.

R is developed specifically to support the concepts and implementation of data science and hence, the support provided by this language is incredible as writing codes become much easier with its simple syntax.

Python is already much popular programming language that can serve more than one development niche without straining even for a bit. The implementation of Python for programming machine learning algorithms is very much popular and the results provided are accurate and faster than any other language. (C or Java). And because of its extended support for data science concept implementation, it becomes a tough competitor for R.

However, if we compare the charts of popularity, Python is obviously more popular among data scientists and developers because of its versatility and easier usage during algorithm implementation. However, R outruns Python when it comes to the packages offered to developers specifically expertise in R over Python. Therefore, to conclude which one of them is the best, let’s take an overview of the features and limits offered by both languages.

Python

Python was first introduced by Guido Van Rossum who developed it as the successor of ABC programming language. Python puts white space at the center while increasing the readability of the developed code. It is a general-purpose programming language that simply extends support for various development needs.

The packages of Python includes support for web development, software development, GUI (Graphical User Interface) development and machine learning also. Using these packages and putting the best development skills forward, excellent solutions can be developed. According to Stackoverflow, Python ranks at the fourth position as the most popular programming language among developers.

Benefits for performing enhanced deep learning using Python are:

Concise and Readable Code
Extended Support from Large Community of Developers
Open-source Programming Language
Encourages Collaborative Coding
Suitable for small and large-scale products

The latest and stable version of Python has been released as Python 3.8.0 on 14th October 2019. Developing a software solution using Python becomes much easier as the extended support offered through the packages drives better development and answers every need.

R is a language specifically used for the development of statistical software and for statistical data analysis. The primary user base of R contains statisticians and data scientists who are analyzing data. Supported by R Foundation for statistical computing, this language is not suitable for the development of websites or applications. R is also an open-source environment that can be used for mining excessive and large amounts of data.

R programming language focuses on the output generation but not the speed. The execution speed of programs written in R is comparatively lesser as producing required outputs is the aim not the speed of the process. To use R in any development or mining tasks, it is required to install its operating system specific binary version before coding to run the program directly into the command line.

R also has its own development environment designed and named RStudio. R also involves several libraries that help in crafting efficient programs to execute mining tasks on the provided data.

The benefits offered by R are pretty common and similar to what Python has to offer:

Open-source programming language
Supports all operating systems
Supports extensions
R can be integrated with many of the languages
Extended Support for Visual Data Mining

Although R ranks at the 17th position in Stackoverflow’s most popular programming language list, the support offered by this language has no match. After all, the R language is developed by statisticians for statisticians!

Python vs R: Should They be Really Compared?

Even when provided with the best technical support and efficient tools, a developer will not be able to provide quality outputs if he/she doesn’t possess the required skills. The point here is, technical skills rank higher than the resources provided. A comparison of these two programming languages is not advisable as they both hold their own set of advantages. However, the developers considering to use both together are less but they obtain maximum benefit from the process.

Both these languages have some features in common. For example, if a representative comes asking you if you lend technical support for developing an uber clone, you are directly going to decline as Python and R both do not support mobile app development. To benefit the most and develop excellent solutions using both these programming languages, it is advisable to stop comparing and start collaborating!

R and Python: How to Fit Both In a Single Program

Anticipating the future needs of the development industry, there has been a significant development to combine these both excellent programming languages into one. Now, there are two approaches to performing this: either we include R script into Python code or vice versa.

Using the available interfaces, packages and extended support from Python we can include R script into the code and enhance the productivity of Python code. Availability of PypeR, pyRserve and more resources helps run these two programming languages efficiently while efficiently performing the background work.

Either way, using the developed functions and packages made available for integrating Python in R are also effective at providing better results. Available R packages like rJython, rPython, reticulate, PythonInR and more, integrating Python into R language is very easy.

Therefore, using the development skills at their best and maximizing the use of such amazing resources, Python and R can be togetherly used to enhance end results and provide accurate deep learning support.

Conclusion

Python and R both are great in their own names and own places. However, because of the wide applications of Python in almost every operation, the annual packages offered to Python developers are less than the developers skilled in using R. However, this doesn’t justify the usability of R. The ultimate decision of choosing between these two languages depends upon the data scientists or developers and their mining requirements.

And if a developer or data scientist decides to develop skills for both- Python and R-based development, it turns out to be beneficial in the near future. Choosing any one or both to use in your project depends on the project requirements and expert support on hand.

Wie der C++-Programmierer bei der Analyse großer Datenmengen helfen kann

February 12, 2020/in Data Mining, Data Science, Data Science News, Education / Certification, Gerneral, Insights, Main Category/by Anastasia Stefanuk

Die Programmiersprache C wurde von Dennis Ritchie in den Bell Labs in einer Zeit (1969-1973) entwickelt, als jeder CPU-Zyklus und jeder Byte Speicher sehr teuer war. Aus diesem Grund wurde C (und später C++) so konzipiert, dass die maximale Leistung der Hardware mit der Sprachkomplexität erzielt werden konnte. Derzeit ist der C++ Programmierer besonders begehrt auf dem Arbeitsmarkt, für ganz bestimmte Abläufe, die wir später genauer beschreiben werden.

Warum sollten Sie einen C++ Entwickler mieten, wenn es um große Daten geht?

C++ ermöglicht, als Sprache auf einem niedrigen Level, eine Feinabstimmung der Leistung der Anwendung in einer Weise, die bei der Verwendung von Sprachen auf einem hohen Level nicht möglich ist. Warum sollten Sie einen C++ Entwickler mieten? C++ bietet den Entwicklern eine viel bessere Kontrolle über den Systemspeicher und die Ressourcen, als die der C Programmierer oder Anderer.

C++ ist die einzige Sprache, in der man Daten mit mehr als 1 GB pro Sekunde knacken, die prädiktive Analyse in Echtzeit neu trainieren und anwenden und vierstellige QPS einer REST-ful API in der Produktion bedienen kann, während die [eventuelle] Konsistenz des Aufzeichnungssystems ständig erhalten bleibt. Auf einem einzigen Server, natürlich aus Gründen der Zuverlässigkeit dupliziert, aber das, ohne in Repliken, Sharding und das Auffüllen und Wiederholen von persistenten Nachrichtenwarteschlangen investieren zu. Für ein groß angelegtes Werbesystem, dynamischen Lastausgleich oder eine hocheffiziente adaptive Caching-Schicht ist C++ die klügste Wahl.

Die allgemeine Vorstellung ist, dass R und Python schneller sind, aber das ist weit von der Wahrheit entfernt. Ein gut optimierter C++-Code könnte hundertmal schneller laufen, als das gleiche Stück Code, das in Python oder R geschrieben wurde. Die einzige Herausforderung bei C++ ist die Menge an Arbeit, die Sie bewältigen müssen, um die fertigen Funktionen zum Laufen zu bringen. Sie müssen wissen, wie man Zeiger verteilt und verwaltet – was ehrlich gesagt ein wenig kompliziert sein kann. Die C# Programmierer Ausbildung ist aus diesem Grunde z.Z. sehr begehrt.

R und Python

Akademiker und Statistiker haben R über zwei Jahrzehnte entwickelt. R verfügt nun über eines der reichsten Ökosysteme, um Datenanalysen durchzuführen. Es sind etwa 12000 Pakete in CRAN (Open-Source-Repository) verfügbar. Es ist möglich, eine Bibliothek zu finden, für was auch immer für eine Analyse Sie durchführen möchten. Die reiche Vielfalt der Bibliothek macht R zur ersten Wahl für statistische Analysen, insbesondere für spezialisierte analytische Arbeiten.

Python kann so ziemlich die gleichen Aufgaben wie R erledigen: Data Wrangling, Engineering, Feature Selection Web Scrapping, App und so weiter. Python ist ein Werkzeug, um maschinelles Lernen in großem Maßstab einzusetzen und zu implementieren. Python-Codes sind einfacher zu warten und robuster als R. Vor Jahren hatte Python nicht viele Bibliotheken für Datenanalyse und maschinelles Lernen. In letzter Zeit holt Python auf und bietet eine hochmoderne API für maschinelles Lernen oder künstliche Intelligenz. Der größte Teil der datenwissenschaftlichen Arbeit kann mit fünf Python-Bibliotheken erledigt werden: Numpy, Pandas, Scipy, Scikit-Learning und Seaborn.

Aber das Wissen, mit Zeigern zu arbeiten oder den Code in C++ zu verwalten, ist mit einem hohen Preis verbunden. Aus diesem Grunde werden C++ Programmierer gesucht, für die Bewältigung von großen Datenpaketen. Ein tiefer Einblick in das Innenleben der Anwendung ermöglicht es ihnen, die Anwendung im Falle von Fehlern besser zu debuggen und sogar Funktionen zu erstellen, die eine Kontrolle des Systems auf Mikroebene erfordern. Schauen Sie sich doch nach C# Entwickler in Berlin um, denn sie haben einen besonders guten Ruf unter den neuen Entwicklern.

Das Erlernen der Programmierung ist eine wesentliche Fähigkeit im Arsenal der Analysten von Big Data. Analysten müssen kodieren, um numerische und statistische Analysen mit großen Datensätzen durchzuführen. Einige der Sprachen, in deren Erlernen auch die C Entwickler Zeit und Geld investieren sollten, sind unter anderem Python, R, Java und C++. Je mehr sie wissen, desto besser – Programmierer sollten immer daran denken, dass sie nicht nur eine einzelne Sprache lernen sollten. C für Java Programmierer sollte ein MUSS sein.

Wo wird das C++ Programmieren eingesetzt?

Die Programmiersprache C++ ist eine etablierte Sprache mit einem großen Satz von Bibliotheken und Tools, die bereit ist, große Datenanwendungen und verteilte Systeme zu betreiben. In den meisten Fällen wird C++ zum Schreiben von Frameworks und Paketen für große Daten verwendet. Diese Programmiersprache bietet auch eine Reihe von Bibliotheken, die beim Schreiben von Algorithmen für das tiefe Lernen helfen. Mit ausreichenden C++-Kenntnissen ist es möglich, praktisch unbegrenzte Funktionen auszuführen. Dennoch ist C++ nicht die Sprache, die man leicht erlernen kann, da man die über 1000 Seiten Spezifikation und fast 100 Schlüsselwörter beherrschen muss.

Die Verwendung von C++ ermöglicht die prozedurale Programmierung für intensive Funktionen der CPU und die Kontrolle über die Hardware, und diese Sprache ist sehr schnell, weshalb sie bei der Entwicklung verschiedener Spiele oder in Spielmaschinen weit verbreitet ist.

C++ bietet viele Funktionen, die anderen Sprachen fehlen. Darüber hinaus bietet die Sprache auch Zugang zu umfangreichen Vorlagen, die es Ihnen ermöglichen, generische Codes zu schreiben. Als betroffenes Unternehmen sollten Sie sich deshalb tatsächlich überlegen, einen C++ Programmierer zu suchen oder in einen Kurs von C++ für Ihren C Programmierer zu investieren. Am Ende lohnen sich bestimmt diese Kosten.

Und vergessen Sie nicht: C++ ist die einzige Sprache, die in der Lage ist, 1 GB+ Daten in weniger als einer Sekunde zu verarbeiten. Darüber hinaus können Sie Ihr Modell neu trainieren und prädiktive Analysen in Echtzeit und sogar die Konsistenz der Systemaufzeichnung anwenden. Diese Gründe machen C++ zu einer bevorzugten Wahl für Sie, wenn Sie einen Datenwissenschaftler für Ihr Unternehmen suchen.

Beispiele für die Verwendung von C++

Die Verwendung von C++ zur Entwicklung von Anwendungen und vielen produktbasierten Programmen, die in dieser Sprache entwickelt wurden, hat mehrere Vorteile, die nur auf ihren Eigenschaften und ihrer Sicherheit beruhen. Unten finden Sie eine Liste der häufigsten Anwendungen von C++.

Google-Anwendungen – Einige der Google-Anwendungen sind auch in C++ geschrieben, darunter das Google-Dateisystem und der Google-Chromium-Browser sowie MapReduce für die Verarbeitung großer Clusterdaten. Die Open-Source-Gemeinschaft von Google hat über 2000 Projekte, von denen viele in den Programmiersprachen C oder C++ geschrieben und bei GitHub frei verfügbar sind.

Mozilla Firefox und Thunderbird – Der Mozilla-Internetbrowser Firefox und der E-Mail-Client Thunderbird sind beide in der Programmiersprache C++ geschrieben, und sie sind ebenfalls Open-Source-Projekte. Der C++-Quellcode dieser Anwendungen ist in den MDN-Webdokumenten zu finden.

Adobe-Systeme – Die meisten der wichtigsten Anwendungen von Adobe-Systemen werden in der Programmiersprache C++ entwickelt. Zu diesen Anwendungen gehören Adobe Photoshop und Image Ready, Illustrator und Adobe Premier. Sie haben in der Vergangenheit eine Menge Open-Source-Codes veröffentlicht, immer in C++, und ihre Entwickler waren in der C++-Community aktiv.

12D-Lösungen – 12D Solutions Pty Ltd ist ein australischer Softwareentwickler, der sich auf Anwendungen im Bereich Bauwesen und Vermessung spezialisiert hat. Computer Aided Design-System für Vermessung, Bauwesen und mehr. Zu den Kunden von 12D Solutions gehören Umweltberater, Berater für Bau- und Wasserbau, lokale, staatliche und nationale Regierungsabteilungen und -behörden, Vermessungsingenieure, Forschungsinstitute, Bauunternehmen und Bergbau-Berater.

In C/C++ geschriebene Betriebssysteme

Apple – Betriebssystem OS XApple – Betriebssystem OS X

Einige Teile von Apple OS X sind in der Programmiersprache C++ geschrieben. Auch einige Anwendungen für den iPod sind in C++ geschrieben.

Microsoft-BetriebssystemeMicrosoft-Betriebssysteme

Der Großteil der Software wird buchstäblich mit verschiedenen Varianten von Visual C++ oder einfach C++ entwickelt. Die meisten der großen Anwendungen wie Windows 95, 98, Me, 200 und XP sind ebenfalls in C++ geschrieben. Auch Microsoft Office, Internet Explorer und Visual Studio sind in Visual C++ geschrieben.

Betriebssystem Symbian – Auch Symbian OS wird mit C++ entwickelt. Dies war eines der am weitesten verbreiteten Betriebssysteme für Mobiltelefone.

Die Einstellung eines C- oder C++-Entwicklers kann eine gute Investition in Ihr Projekt-Upgrade sein

Normalerweise benötigen C- und C++-Anwendungen weniger Strom, Speicher und Platz als die Sprachen der virtuellen Maschinen auf hoher Ebene. Dies trägt dazu bei, den Kapitalaufwand, die Betriebskosten und sogar die Kosten für die Serverfarm zu reduzieren. Hier zeigt sich, dass C++ die Gesamtentwicklungskosten erheblich reduziert.

Trotz der Tatsache, dass wir eine Reihe von Tools und Frameworks nur für die Verwaltung großer Daten und die Arbeit an der Datenwissenschaft haben, ist es wichtig zu beachten, dass auf all diesen modernen Frameworks eine Schicht einer niedrigen Programmiersprache – wie C++ – aufgesetzt ist. Die Niedrigsprachen sind für die tatsächliche Ausführung des dem Framework zugeführten Hochsprachencodes verantwortlich. Es ist also ratsam in ein C-Entwickler-Gehalt zu investieren.

Der Grund dafür, dass C++ ein so unverzichtbares Werkzeug ist, liegt darin, dass es nicht nur einfach, sondern auch extrem leistungsfähig ist und zu den schnellsten Sprachen auf dem Markt gehört. Darüber hinaus verfügt ein gut geschriebenes Programm in C++ über ein komplexes Wissen und Verständnis der Architektur der Maschine, sowie der Speicherzugriffsmuster und kann schneller laufen als andere Programme. Es wird Ihrem Unternehmen Zeit- und Stromkosten sparen.

Zum Abschluss eine Grafik, die Sie als Unternehmer interessieren wird und die das Verhältnis von der Performance and der Sicherheit diverser Sprachen darstellt:

Aus diesen und weiteren Gründen neigen viele Unternehmensentwickler und Datenwissenschaftler mit massiven Anforderungen an Skalierbarkeit und Leistung zu dem guten alten C++. Viele Organisationen, die Python oder andere Hochsprachen für die Datenanalyse und Erkundungsaufgaben verwenden, verlassen sich auf C++, um Programme zu entwickeln, die diese Daten an die Kunden weiterleiten – in Echtzeit.

Multi-touch attribution: A data-driven approach

February 4, 2020/in Data Science, Gerneral, Insights, Python, R Statistics, Tutorial, Use Case, Use Cases, Visualization/by Aakash Chugh

This is the first article of article series Getting started with the top eCommerce use cases.

What is Multi-touch attribution?

Customers shopping behavior has changed drastically when it comes to online shopping, as nowadays, customer likes to do a thorough market research about a product before making a purchase. This makes it really hard for marketers to correctly determine the contribution for each marketing channel to which a customer was exposed to. The path a customer takes from his first search to the purchase is known as a Customer Journey and this path consists of multiple marketing channels or touchpoints. Therefore, it is highly important to distribute the budget between these channels to maximize return. This problem is known as multi-touch attribution problem and the right attribution model helps to steer the marketing budget efficiently. Multi-touch attribution problem is well known among marketers. You might be thinking that if this is a well known problem then there must be an algorithm out there to deal with this. Well, there are some traditional models but every model has its own limitation which will be discussed in the next section.

Traditional attribution models

Most of the eCommerce companies have a performance marketing department to make sure that the marketing budget is spent in an agile way. There are multiple heuristics attribution models pre-existing in google analytics however there are several issues with each one of them. These models are:

First touch attribution model

100% credit is given to the first channel as it is considered that the first marketing channel was responsible for the purchase.

Figure 1: First touch attribution model

Last touch attribution model

100% credit is given to the last channel as it is considered that the first marketing channel was responsible for the purchase.

Figure 2: Last touch attribution model

Linear-touch attribution model

In this attribution model, equal credit is given to all the marketing channels present in customer journey as it is considered that each channel is equally responsible for the purchase.

Figure 3: Linear attribution model

U-shaped or Bath tub attribution model

This is most common in eCommerce companies, this model assigns 40% to first and last touch and 20% is equally distributed among the rest.

Figure 4: Bathtub or U-shape attribution model

Data driven attribution models

Traditional attribution models follows somewhat a naive approach to assign credit to one or all the marketing channels involved. As it is not so easy for all the companies to take one of these models and implement it. There are a lot of challenges that comes with multi-touch attribution problem like customer journey duration, overestimation of branded channels, vouchers and cross-platform issue, etc.

Switching from traditional models to data-driven models gives us more flexibility and more insights as the major part here is defining some rules to prepare the data that fits your business. These rules can be defined by performing an ad hoc analysis of customer journeys. In the next section, I will discuss about Markov chain concept as an attribution model.

Markov chains

Markov chains concepts revolves around probability. For attribution problem, every customer journey can be seen as a chain(set of marketing channels) which will compute a markov graph as illustrated in figure 5. Every channel here is represented as a vertex and the edges represent the probability of hopping from one channel to another. There will be an another detailed article, explaining the concept behind different data-driven attribution models and how to apply them.

Figure 5: Markov chain example

Challenges during the Implementation

Transitioning from a traditional attribution models to a data-driven one, may sound exciting but the implementation is rather challenging as there are several issues which can not be resolved just by changing the type of model. Before its implementation, the marketers should perform a customer journey analysis to gain some insights about their customers and try to find out/perform:

Length of customer journey.
On an average how many branded and non branded channels (distinct and non-distinct) in a typical customer journey?
Identify most upper funnel and lower funnel channels.
Voucher analysis: within branded and non-branded channels.

When you are done with the analysis and able to answer all of the above questions, the next step would be to define some rules in order to handle the user data according to your business needs. Some of the issues during the implementation are discussed below along with their solution.

Customer journey duration

Assuming that you are a retailer, let’s try to understand this issue with an example. In May 2016, your company started a Fb advertising campaign for a particular product category which “attracted” a lot of customers including Chris. He saw your Fb ad while working in the office and clicked on it, which took him to your website. As soon as he registered on your website, his boss called him (probably because he was on Fb while working), he closed everything and went for the meeting. After coming back, he started working and completely forgot about your ad or products. After a few days, he received an email with some offers of your products which also he ignored until he saw an ad again on TV in Jan 2019 (after 3 years). At this moment, he started doing his research about your products and finally bought one of your products from some Instagram campaign. It took Chris almost 3 years to make his first purchase.

Figure 6: Chris journey

Now, take a minute and think, if you analyse the entire journey of customers like Chris, you would realize that you are still assigning some of the credit to the touchpoints that happened 3 years ago. This can be solved by using an attribution window. Figure 6 illustrates that 83% of the customers are making a purchase within 30 days which means the attribution window here could be 30 days. In simple words, it is safe to remove the touchpoints that happens after 30 days of purchase. This parameter can also be changed to 45 days or 60 days, depending on the use case.

Figure 7: Length of customer journey

Removal of direct marketing channel

A well known issue that every marketing analyst is aware of is, customers who are already aware of the brand usually comes to the website directly. This leads to overestimation of direct channel and branded channels start getting more credit. In this case, you can set a threshold (say 7 days) and remove these branded channels from customer journey.

Figure 8: Removal of branded channels

Cross platform problem

If some of your customers are using different devices to explore your products and you are not able to track them then it will make retargeting really difficult. In a perfect world these customers belong to same journey and if these can’t be combined then, except one, other paths would be considered as “non-converting path”. For attribution problem device could be thought of as a touchpoint to include in the path but to be able to track these customers across all devices would still be challenging. A brief introduction to deterministic and probabilistic ways of cross device tracking can be found here.

Figure 9: Cross platform clash

How to account for Vouchers?

To better account for vouchers, it can be added as a ‘dummy’ touchpoint of the type of voucher (CRM,Social media, Affiliate or Pricing etc.) used. In our case, we tried to add these vouchers as first touchpoint and also as a last touchpoint but no significant difference was found. Also, if the marketing channel of which the voucher was used was already in the path, the dummy touchpoint was not added.

Figure 10: Addition of Voucher as a touchpoint

Let me know in comments if you would like to add something or if you have a different perspective about this use case.

Tag Archive for: Python

1 Preface

2 Tokens and word embedding

3 Language model

Appendix

[References]

This is the fifth of the article series “5 tips for clean coding” to follow as soon as you’ve made the first steps into your coding career, in this article series. Read the introduction here, to find out why it is important to write clean code if you missed it.

References:

This is the third of the article series “5 tips for clean coding” to follow as soon as you’ve made the first steps into your coding career, in this article series. Read the introduction here, to find out why it is important to write clean code if you missed it.

References:

This is the second of the article series “5 tips for clean coding” to follow as soon as you’ve made the first steps into your coding career, in this article series. Read the introduction here, to find out why it is important to write clean code if you missed it.

This is the first of the article series “5 tips for clean coding” to follow as soon as you’ve made the first steps into your coding career, in this article series. Read the introduction here, to find out why it is important to write clean code if you missed it.

References:

This series of articles will cover 5 clean coding tips to follow as soon as you’ve made the first steps into your coding career, with the example of python.

List of articles in this series:

References:

Warum sollten Sie einen C++ Entwickler mieten, wenn es um große Daten geht?

R und Python

Wo wird das C++ Programmieren eingesetzt?

Beispiele für die Verwendung von C++

Die Einstellung eines C- oder C++-Entwicklers kann eine gute Investition in Ihr Projekt-Upgrade sein

What is Multi-touch attribution?

Traditional attribution models

First touch attribution model

Last touch attribution model

Linear-touch attribution model

U-shaped or Bath tub attribution model

Data driven attribution models

Markov chains

Challenges during the Implementation

Customer journey duration

Removal of direct marketing channel

Cross platform problem

How to account for Vouchers?

Interesting links

Pages

Categories

Archive