電力現(xiàn)貨市場現(xiàn)貨需求

Note from Towards Data Science’s editors: While we allow independent authors to publish articles in accordance with our rules and guidelines, we do not endorse each author’s contribution. You should not rely on an author’s works without seeking professional advice. See our Reader Terms for details.

Towards Data Science編輯的注意事項： 盡管我們允許獨(dú)立作者按照我們的 規(guī)則和指南 發(fā)表文章 ，但我們不認(rèn)可每位作者的貢獻(xiàn)。 您不應(yīng)在未征求專業(yè)意見的情況下依賴作者的作品。 有關(guān) 詳細(xì)信息， 請參見我們的 閱讀器條款 。

介紹 (Introduction)

After Iron and Aluminium, Copper is one of the most consumed metals in the World. An extremely versatile metal, Copper’s electrical and thermal conductivity, antimicrobial, and corrosion-resistant properties lend the metal to widespread application in most sectors of the economy. From power infrastructure, homes, and factories to electronics and medical equipment, the global economic dependency on Copper is so profound that it is sometimes referred to as ‘Dr. Copper’, and is often cited as such by market and commodity analysts because of the metal’s ability to assess global economic health and activity.

一壓腳提升鋼鐵，鋁，銅是在消費(fèi)最多的金屬之一的世界 。 銅具有極強(qiáng)的通用性，其導(dǎo)電性和導(dǎo)熱性，抗菌性和耐腐蝕性能使該金屬在大多數(shù)經(jīng)濟(jì)領(lǐng)域得到廣泛應(yīng)用。 從電力基礎(chǔ)設(shè)施，住宅，工廠到電子設(shè)備和醫(yī)療設(shè)備，全球?qū)︺~的經(jīng)濟(jì)依存度非常高，以至于有時被稱為“ 銅博士 ”，并且由于受到市場和商品分析師的歡迎，因此經(jīng)常被稱為“ 銅博士 ”。金屬評估全球經(jīng)濟(jì)健康和活動的能力。

From a trading perspective, Copper pricing is determined by the supply and demand dynamics on the metal exchanges, particularly the London Metal Exchange (LME) and the Chicago Mercantile Exchange (CME) COMEX. The price Copper trades at, however, is affected by innumerable factors, many of which are very difficult to measure concurrently :

從交易的角度來看，銅價取決于金屬交易所(尤其是倫敦金屬交易所(LME)和芝加哥商業(yè)交易所(CME)COMEX )的供求動態(tài)。 但是，銅的交易價格受到眾多因素的影響，其中許多因素很難同時衡量：

• Global economic growth (GDP)
  全球經(jīng)濟(jì)增長(GDP)
• Emerging market economies
  新興市場經(jīng)濟(jì)

• China’s economy (China accounts for half of the global Copper demand)

  中國的經(jīng)濟(jì)( 中國占全球銅需求的一半 )

• Political and environmental instability in Copper ore producing countries
  銅礦生產(chǎn)國的政治和環(huán)境動蕩
• The U.S. housing market
  美國住房市場
• Trade sanctions & tariffs
  貿(mào)易制裁與關(guān)稅
• Many, many others.
  很多很多。

As well as the aforementioned fundamental factors, Copper’s price can also be artificially influenced by hedge funds, investment institutions, bonded metal, and even domestic trading. From a systematic trading point of view, this makes for a very challenging situation when we want to develop a predictive model.

除上述基本因素外，對沖基金，投資機(jī)構(gòu)， 金屬保稅甚至國內(nèi)交易也可能人為地影響銅價。 從系統(tǒng)的交易角度來看，當(dāng)我們要開發(fā)預(yù)測模型時，這將帶來非常具有挑戰(zhàn)性的情況。

Short-term opportunities can exist however, in relation to events that are announced in the form of news. The spot and forward price of Copper has been buffeted throughout the US-China trade war and like all markets, responds almost instantly to major news announcements.

但是，對于以新聞形式宣布的事件，可能存在短期機(jī)會。 在美中貿(mào)易戰(zhàn)期間 ，銅的現(xiàn)貨價格和遠(yuǎn)期價格一直受到打擊，并且像所有市場一樣，銅價幾乎立即回應(yīng)了重大新聞公告。

Caught early enough, NLP-based systematic trading models can capitalize on these short-term price movements through parsing the announcements as a vector of tokens, evaluating the underlying sentiment, and subsequently taking a position prior to the anticipated (if applicable) price move, or, during the movement in the hope of capitalizing on a potential correction.

盡早發(fā)現(xiàn)基于NLP的系統(tǒng)交易模型，可以通過將公告作為代幣的載體進(jìn)行解析，評估基本情緒并隨后在預(yù)期(如果適用)的價格變動之前持倉來利用這些短期價格變動，或者，在運(yùn)動中希望利用可能的修正。

問題 (Problem)

In this article, we are going to scrape historical (and current) tweets from a variety of financial news publications Twitter feeds. We will then analyse this data in order to understand the underlying sentiment behind each tweet, develop a sentiment score, and examine the correlation between this score and Copper’s spot price over the last five years.

在本文中，我們將從各種金融新聞出版物Twitter提要中抓取歷史(和當(dāng)前)推文。 然后，我們將分析此數(shù)據(jù)，以便了解每條推文背后的基本情緒，得出情緒評分，并檢查該評分與最近五年銅價之間的相關(guān)性。

We will cover:

我們將介紹：

How to obtain historic tweets with GetOldTweets3.

如何使用GetOldTweets3 獲取歷史性推文 。

Basic Exploratory Data Analysis (EDA) techniques with our Twitter data.

我們的Twitter數(shù)據(jù)的基本探索性數(shù)據(jù)分析 (EDA)技術(shù)。

Text data preprocessing techniques (Stopwords, tokenization, n-grams, Stemming & lemmatization etc).

文本數(shù)據(jù)預(yù)處理技術(shù) (停止詞，標(biāo)記化，n-gram，詞干和詞根化等)。

Latent Dirichlet Allocation to model & explore the distribution of topics and content their content within our Twitter data using GenSim & NLTK PyLDAvis.

使用GenSim和NLTK PyLDAvis， 潛在的Dirichlet分配可以在我們的Twitter數(shù)據(jù)中建模和探索主題的分布和內(nèi)容的內(nèi)容。

Sentiment scoring with NLTK Valence Aware Dictionary and sEntiment Reasoner (VADER).

使用NLTK價意識字典和情感推理器( VADER )進(jìn)行 情感評分 。

We will not go as far as developing and testing a fully-fledged trading strategy off the back of this work, the semantics of which is beyond the scope of this article. Moreover, this article is intended to demonstrate the various techniques a Data Scientist can employ to extract signals from text data in the search for profitable signals.

我們將不去開發(fā)和測試一種成熟的交易策略，因?yàn)樗恼Z義超出了本文的范圍。 此外，本文旨在演示數(shù)據(jù)科學(xué)家可以使用多種技術(shù)從文本數(shù)據(jù)中提取信號以尋找有利的信號。

現(xiàn)貨銅NLP策略模型 (Spot Copper NLP Strategy Model)

Let’s kick off by acquiring our data.

讓我們開始獲取數(shù)據(jù)。

現(xiàn)貨價格數(shù)據(jù) (Spot Price Data)

We will start by acquiring our spot Copper price data. The reason behind our choice to use Copper’s spot price, rather than a Copper forward contract (an agreement to buy or sell a fixed amount of metal for delivery on an agreed fixed future date at a price agreed today) is that the spot price is the most reactive to market events — it is an offer to complete a commodity transaction immediately. Normally, we would use a Bloomberg terminal to acquire this data, however, we can get historical spot Copper data for free from Business Insider:

我們將從獲取現(xiàn)貨銅價格數(shù)據(jù)開始。 我們選擇使用銅的現(xiàn)貨價格而不是銅遠(yuǎn)期合約 (以今天商定的價格在約定的固定未來日期買賣固定數(shù)量的金屬以進(jìn)行交割的協(xié)議)的原因是，現(xiàn)貨價格是對市場事件最有React-它是立即完成商品交易的要約。 通常，我們將使用彭博終端機(jī)來獲取此數(shù)據(jù)，但是，我們可以從Business Insider免費(fèi)獲取歷史現(xiàn)貨銅數(shù)據(jù)：

# Imports
import glob
import GetOldTweets3 as got
import gensim as gs
import os
import keras
import matplotlib.pyplot as plt
import numpy as np
import nltk
import pandas as pd
import pyLDAvis.gensim
import re
import seaborn as snsfrom keras.preprocessing.text import Tokenizer
from nltk.stem import *
from nltk.util import ngrams
from nltk.corpus import stopwords
from nltk.tokenize import TweetTokenizer
from nltk.sentiment.vader import SentimentIntensityAnalyzer
from sklearn.feature_extraction.text import CountVectorizer
from tensorflow.keras.preprocessing.sequence import pad_sequences# Get Cu Spot
prices_df = pd.read_csv(
'/content/Copper_120115_073120',
parse_dates=True,
index_col='Date'
)
# To lower case
cu_df.columns = cu_df.columns.str.lower()#Plt close price
cu_df['close'].plot(figsize=(16,4))
plt.ylabel('Spot, $/Oz')
plt.title('Cu Spot Close Price, $/Oz')
plt.legend()
plt.grid()Spot Copper, Close Price, 2015–01–01 to 2020–07–01, $/Mt現(xiàn)貨銅，收盤價，2015-01-01至2020-07-01，美元/噸

Whilst our price data looks fine, it is important to note that we are considering daily price data. Consequently, we are limiting ourselves to a timeframe that could see us losing information — any market reaction to a news event is likely to take place within minutes, likely seconds of its announcement. Ideally, we would be using 1–5-minute bars, but for the purposes of this article, this will do ok.

雖然我們的價格數(shù)據(jù)看起來不錯，但需要注意的是，我們正在考慮每日價格數(shù)據(jù)。 因此，我們將自己限制在一個可能使我們丟失信息的時間表上-對新聞事件的任何市場React都可能在幾分鐘之內(nèi)發(fā)生，可能在新聞發(fā)布幾秒鐘后發(fā)生。 理想情況下，我們將使用1-5分鐘的柱線，但是出于本文的目的，這沒關(guān)系。

推文數(shù)據(jù) (Tweet Data)

We will extract our historical tweet data using a library called GetOldTweets3 (GOT). Unlike the official Twitter API, GOT3 enables users to access an extensive history of twitter data. Given a list of Twitter handles belonging to financial news outlets and a few relevant keywords, we can define the search parameters over which we want to get data for (note: I have posted a screenshot, rather than a code snippet, of the requisite logic to perform this action below for formatting reasons):

我們將使用名為GetOldTweets3 (GOT)的庫提取歷史推文數(shù)據(jù)。 與官方的Twitter API不同，GOT3使用戶可以訪問Twitter數(shù)據(jù)的廣泛歷史記錄。 給定屬于金融新聞媒體的Twitter句柄列表和一些相關(guān)的關(guān)鍵字，我們可以定義要為其獲取數(shù)據(jù)的搜索參數(shù)( 注意：我已發(fā)布了必要邏輯的屏幕截圖，而不是代碼段)出于格式化原因在下面執(zhí)行此操作)：

Get historical twitter data for specified handles w.r.t search parameters獲取指定手柄句柄wrt搜索參數(shù)的歷史Twitter數(shù)據(jù)

The method .setQuerySearch() accepts a single search query, so we are unable to extract tweets for multiple search criteria. We can easily solve this limitation using a loop. For example, one could simply assign variable names to each execution of a unique query, i.e. ‘spot copper’, ‘copper prices’ etc, but for the purposes of this article we can settle for a single query:

.setQuerySearch()方法接受單個搜索查詢，因此我們無法為多個搜索條件提取推文。 我們可以使用循環(huán)輕松解決此限制。 例如，可以為每次查詢的每次執(zhí)行簡單地分配變量名稱，即“現(xiàn)貨銅價”，“銅價”等，但是出于本文的目的，我們可以解決一個查詢：

# Define handles
commodity_sources = ['reuters','wsj','financialtimes', 'bloomberg']# Query
search_terms = 'spot copper'# Get twitter data
tweets_df = get_tweets(
commodity_sources,
search_term = search_terms,
top_only = False,
start_date = '2015-01-01',
end_date = '2020-01-01'
).sort_values('date', ascending=False).set_index('date')tweets_df.head(10)Historical Twitter Data歷史Twitter數(shù)據(jù)

So far so good.

到目前為止，一切都很好。

We now need to process this text data in order to make it interpretable for our topic and sentiment models.

現(xiàn)在，我們需要處理此文本數(shù)據(jù)，以使其對于我們的主題和情感模型可解釋。

預(yù)處理和探索性數(shù)據(jù)分析 (Preprocessing & Exploratory Data Analysis)

Preprocessing of text data for Natural Language applications requires careful consideration. Composing a numerical vector from text data can be challenging from a loss point of view, with valuable information and subject context easily lost when performing seemingly basic tasks such as removing stopwords, as we shall see next.

對于自然語言應(yīng)用程序，文本數(shù)據(jù)的預(yù)處理需要仔細(xì)考慮。 從丟失的角度來看，從文本數(shù)據(jù)組成數(shù)字矢量可能具有挑戰(zhàn)性，當(dāng)執(zhí)行看似基本的任務(wù)(例如刪除停用詞)時，有價值的信息和主題上下文很容易丟失，我們將在后面看到。

Firstly, let's remove redundant information in the form of tags and URLs, i.e.

首先，讓我們以標(biāo)記和URL的形式刪除多余的信息，即

Tweets from media outlets typically contain handle tags, hashtags, and links to articles, all of which need removing.來自媒體的推文通常包含句柄標(biāo)簽，主題標(biāo)簽和指向文章的鏈接，所有這些都需要刪除。

We define a couple of one-line Lambda functions that use Regex to remove the letters and characters matching the expressions we want to remove:

我們定義了幾個單行Lambda函數(shù)，這些函數(shù)使用Regex刪除與要刪除的表達(dá)式匹配的字母和字符：

#@title Strip chars & urls
remove_handles = lambda x: re.sub(‘@[^\s]+’,’’, x)
remove_urls = lambda x: re.sub(‘http[^\s]+’,’’, x)
remove_hashtags = lambda x: re.sub('#[^\s]*','',x)tweets_df[‘text’] = tweets_df[‘text’].apply(remove_handles)
tweets_df[‘text’] = tweets_df[‘text’].apply(remove_urls)
tweets_df[‘text’] = tweets_df[‘text’].apply(remove_hashtags)

Next, we perform some fundamental analysis of our twitter data by examining tweet composition, such as individual tweet lengths (words per tweet), number of characters, etc.

接下來，我們通過檢查tweet組成對Twitter數(shù)據(jù)進(jìn)行一些基礎(chǔ)分析，例如各個tweet長度(每條tweet的單詞數(shù))，字符數(shù)等。

Basic Text EDA — Word & Character Frequency Distributions基本文本EDA —單詞和字符的頻率分布

停用詞 (Stop Words)

It is immediately apparent that the mean length of each tweet is relatively short (10.3 words, to be precise). This information suggests that at the expense of computational complexity and memory overhead, filtering stopwords might not be a good idea if we consider the potential information loss.

顯而易見，每條推文的平均長度都比較短(準(zhǔn)確地說是10.3個字)。 此信息表明，如果考慮潛在的信息丟失，則以計算復(fù)雜性和內(nèi)存開銷為代價，過濾停用詞可能不是一個好主意。

Initially, this experiment was trialled with having all stop words removed from Tweets, using NLTK’s very handy standard list of Stop Words:

最初，該實(shí)驗(yàn)使用NLTK非常方便的標(biāo)準(zhǔn)停用詞列表，從Tweets中刪除了所有停用詞，進(jìn)行了試驗(yàn)：

# Standard tweet sw
stop_words_nltk = set(stopwords.words('english'))# custom stop words
stop_words = get_top_ngram(tweets_df['text'], 1)
stop_words_split = [
w[0] for w in stop_words
if w[0] not in [
'price', 'prices',
'china', 'copper',
'spot', 'other_stop_words_etc'
] # Keep SW with hypothesised importance
]stop_words_all = list(stop_words_nltk) + stop_words_split

However, this action lead to a lot of miscategorised tweets (from a sentiment score point-of-view) which supports the notion of loss of information, and therefore best avoided.

但是，此操作會導(dǎo)致很多錯誤分類的推文(從情感評分的角度來看)，這些推文支持信息丟失的概念，因此最好避免。

At this point, It is well worth highlighting NLTK’s excellent library when it comes to dealing with Twitter data. It offers a comprehensive suite of tools and functions to help parse social media outputs, including emoticon interpretation!. One can find a really helpful guide to getting started with and using NLTK on Twitter data here.

在這一點(diǎn)上，當(dāng)涉及到Twitter數(shù)據(jù)時，非常值得強(qiáng)調(diào)NLTK的出色庫。 它提供了一套全面的工具和功能來幫助解析社交媒體輸出，包括表情釋義！ 人們可以找到一個真正的幫助指導(dǎo)入門，并在Twitter上的數(shù)據(jù)使用NLTK 這里 。

克 (N-grams)

The next step is to consider word order. When we vectorize a sequence of tokens into a bag-of-words (BOW — more on this in the next paragraph), we lose both context and meaning inherent in the order those words within a tweet. We can attempt to understand the importance of word order within our tweets DataFrame by examining the most frequent n-grams.

下一步是考慮單詞順序。 當(dāng)我們將標(biāo)記序列向量化為單詞袋時(BOW-下一節(jié)將對此進(jìn)行詳細(xì)介紹)，我們將失去上下文和含義，這些上下文和含義是推文中這些單詞所固有的順序。 我們可以通過檢查最頻繁的n-gram來嘗試了解推文DataFrame中單詞順序的重要性。

As observed in our initial analysis above, the average length of a given tweet is only 10 words. In light of this information, the order of words within a tweet and, specifically, ensuring we retain the context and meaning inherent within this ordering, is critical to generating an accurate sentiment score. We can extend the concept of a token to include multiword tokens i.e. n-grams in order to retain the meaning within the ordering of words.

正如我們在上文的初步分析中所觀察到的，給定推文的平均長度僅為10個字。 根據(jù)這些信息，一條推文中的單詞順序 ，特別是確保我們保留該順序中固有的上下文和含義， 對于生成準(zhǔn)確的情感評分至關(guān)重要 。 我們可以將令牌的概念擴(kuò)展為包括多字令牌(即n-gram) ，以便將含義保留在單詞的順序內(nèi)。

NLTK has a very handy (and very efficient) n-gram tokenizer: from nltk.util import ngram. The n-gram function returns a generator that yields the top “n” n-grams as tuples. We, however, are interested in exploring what these n-grams actually are so will in the first instance, so will make use of Scikit-learn’s CountVectorizer to parse our tweet data:

NLTK有一個非常方便(且非常有效)的n-gram令牌生成器： from nltk.util import ngram 。 n-gram函數(shù)返回一個生成器，該生成器生成前“ n”個n-gram作為元組。 但是，我們有興趣首先探索這些n-gram的實(shí)際含義，因此將利用Scikit-learn的CountVectorizer來解析我們的tweet數(shù)據(jù)：

def get_ngrams(doc, n=None):
"""
Get matrix of individual token counts for a given text document.
Args:
corpus: String, the text document to be vectorized into its constituent tokens.
n: Int, the number of contiguous words (n-grams) to return.
Returns:
word_counts: A list of word:word frequency tuples.
"""
# Instantiate CountVectorizer class
vectorizer = CountVectorizer(ngram_range=
(n,n)).fit(doc)
bag_of_words = vectorizer.transform(doc)
sum_of_words = bag_of_words.sum(axis=0)
# Get word frequencies
word_counts = [(word, sum_of_words[0, index])
for word, index in vectorizer.vocabulary_.items()
]
word_counts = sorted(word_counts, key=lambda x:x[1], reverse=True)
return word_counts# Get n-grams
top_bigrams = get_ngrams(tweets_df['text'], 2)[:20]
top_trigrams = get_ngrams(tweets_df['text'], 3)[:20]Contiguous Word Frequencies (n-grams).連續(xù)字頻率(n克)。

Upon examination of our n-gram plots, we can see that apart from a few exceptions, an NLP-based predictive model would learn significantly more from our n-gram features. For example, the model will be able to correctly interpret ‘copper price’ as a reference to the physical price of copper, or ‘china trade’ to China’s trade, rather than interpreting the individual word’s meaning.

通過檢查我們的n元語法圖，我們可以看到，除了少數(shù)例外，基于NLP的預(yù)測模型將從n元語法特征中學(xué)習(xí)更多。 例如，該模型將能夠正確地將“銅價”解釋為對銅的實(shí)物價格的參考 ，或者將“中國貿(mào)易”解釋為對中國貿(mào)易的參考，而不是解釋單個詞的含義。

令牌化和合法化。 (Tokenization & Lemmatization.)

Our next step is to tokenize our tweets for use in our LDA topic model. We will develop a function that will perform the necessary segmentation of our tweets (the Tokenizer’s job) and Lemmatization.

下一步是標(biāo)記要在LDA主題模型中使用的推文。 我們將開發(fā)一個函數(shù)，該函數(shù)將對我們的tweet(Tokenizer的工作)和Lemmatization進(jìn)行必要的分段。

We will use NLTK’s TweetTokenizer to perform the tokenization of our tweets, which has been developed specifically to parse tweets and understand their semantics relative to this social media platform.

我們將使用NLTK的TweetTokenizer來對我們的tweet進(jìn)行令牌化，該令牌是專門為解析tweet并了解其相對于此社交媒體平臺的語義而開發(fā)的。

Given the relatively brief nature of each tweet, dimensionality reduction is not so much of a pressing issue for our model. With this in mind, it is reasonable not to perform any Stemming operations on our data in an attempt to eliminate the small meaning differences in the plural vs possessive forms of words.

考慮到每條推文的相對簡短性，降維并不是我們模型的緊迫問題。 考慮到這一點(diǎn)，合理的做法是不對我們的數(shù)據(jù)執(zhí)行任何詞干操作，以消除單詞的復(fù)數(shù)形式和所有格形式中的微小含義差異。

We shall instead implement a Lemmatizer, WordNetLemmatizer, to normalise the words within our tweet data. Lemmatisation is arguably more accurate than stemming for our application as it takes into account a word’s meaning. WordNetLemmatizer can also help improve the accuracy of our topic model as it utilises part of speech (POS) tagging. The POS tag for a word indicates its role in the grammar of a sentence, such as drawing the distinction between a noun POS and an adjective POS, like “Copper” and “Copper’s price”.

相反，我們將實(shí)現(xiàn)一個Lemmatizer WordNetLemmatizer ，以規(guī)范我們tweet數(shù)據(jù)中的單詞。 對于我們的應(yīng)用程序， 詞法化可能要比詞干化更為準(zhǔn)確，因?yàn)樗紤]了單詞的含義 。 WordNetLemmatizer利用詞性(POS)標(biāo)記，還可以幫助提高主題模型的準(zhǔn)確性。 單詞的POS標(biāo)簽指示其在句子語法中的作用，例如繪制名詞POS和形容詞POS(例如“ Copper”和“ Copper's price”)之間的區(qū)別。

Note: You must configure the POS tags manually within WordNetLemmatizer. Without a POS tag, it assumes everything you feed it is a noun.

注意：您必須在WordNetLemmatizer中手動配置POS標(biāo)簽。 沒有POS標(biāo)簽，它將假定您提供的所有內(nèi)容都是一個名詞。

def preprocess_tweet(df: pd.DataFrame, stop_words: None):
"""
Tokenize and Lemmatize raw tweets in a given DataFrame.
Args:
df: A Pandas DataFrame of raw tweets indexed by index of type DateTime.
stop_words: Optional. A list of Strings containing stop words to be removed.
Returns:
processed_tweets: A list of preprocessed tokens of type String.
"""
processed_tweets = []
tokenizer = TweetTokenizer()
lemmatizer = WordNetLemmatizer()
for text in df['text']:
words = [w for w in tokenizer.tokenize(text) if (w not in stop_words)]
words = [lemmatizer.lemmatize(w) for w in words if len(w) > 2] processed_tweets.append(words)
return processed_tweets# Tokenize & normalise tweets
tweets_preprocessed = preprocess_tweet(tweets_df, stop_words_all)

For the purposes of demonstrating the utility of the above function, we have also passed a list of stop words into the function.

為了演示上述功能的實(shí)用性，我們還向該功能傳遞了停用詞列表。

矢量化和連續(xù)詞袋 (Vectorisation & Continuous Bag-Of-Words)

We now need to convert our tokenised tweets to vectors, using a document representation method known as a Bag Of Words (BOW). In order to perform this mapping, we will use Gensim’s Dictionary class:

現(xiàn)在，我們需要使用一種稱為詞義(BOW)的文檔表示方法，將標(biāo)記化的推文轉(zhuǎn)換為向量。 為了執(zhí)行此映射，我們將使用Gensim的Dictionary類 ：

tweets_dict = gs.corpora.Dictionary(tweets_preprocessed)

By passing the list of processed tweets as an argument, Gensim’s Dictionary creates a unique integer id mapping for each unique, normalised word (similar to a Hash Map). We can view the word: id mapping by calling .token2id()on our tweets_dict. We then count the number of occurrences of each distinct word, convert the word to its integer word id, and return the result as a sparse vector:

通過將已處理的推文列表作為參數(shù)傳遞，Gensim的詞典為每個唯一的標(biāo)準(zhǔn)化單詞創(chuàng)建一個唯一的整數(shù)id映射(類似于Hash Map )。 我們可以通過在tweets_dict上調(diào)用.token2id()來查看單詞：id映射。 然后，我們計算每個不同單詞的出現(xiàn)次數(shù)，將該單詞轉(zhuǎn)換為其整數(shù)單詞id，然后將結(jié)果作為稀疏向量返回：

cbow_tweets = [tweets_dict.doc2bow(doc) for doc in tweets_preprocessed]

LDA主題建模 (LDA Topic Modelling)

Now for the fun part.

現(xiàn)在是有趣的部分。

A precursor to developing our NLP-based trading strategy is to understand whether the data we have extracted contains topics/signals that are relevant to the price of Copper, and, more importantly, whether it contains information that we could potentially trade on.

制定基于NLP的交易策略的先驅(qū)是了解我們提取的數(shù)據(jù)是否包含與銅價相關(guān)的主題/信號，更重要的是，它是否包含我們可能進(jìn)行交易的信息。

This requires us to examine and evaluate the various topics and the words that are representative of these topics within our data. Garbage in, garbage out.

這就要求我們檢查和評估數(shù)據(jù)中的各個主題以及代表這些主題的詞語。 垃圾進(jìn)垃圾出。

In order to explore the various topics (and the subjects of said topics) within our tweet corpus, we will use Gensim’s Latent Dirichlet Allocation model. LDA is a generative probabilistic model applicable to collections of discrete data such as text. LDA functions as a hierarchical Bayesian model in which each item in a collection is modelled as a finite mixture over an underlying set of topics. Each topic is, in turn, modelled as an infinite mixture over an underlying set of topic probabilities (Blei, Ng et al 2003).

為了探索我們推文語料庫中的各個主題(以及所述主題的主題)，我們將使用Gensim的潛在Dirichlet分配模型。 LDA是適用于離散數(shù)據(jù)(例如文本)集合的生成概率模型。 LDA用作分層貝葉斯模型，其中將集合中的每個項目建模為基礎(chǔ)主題集上的有限混合。 每個主題依次被建模為主題概率的基礎(chǔ)上的無限混合( Blei，Ng等，2003 )。

We pass our newly vectorized tweets, cbow_tweetsand the dictionary mapping each word to an id, tweets_dictto Gensim’s LDA Model Class:

我們通過我們的新矢量鳴叫， cbow_tweets和字典映射每個單詞的ID， tweets_dict到Gensim的LDA模型類：

# Instantiate model
model = gs.models.LdaMulticore(
cbow_tweets,
num_topics = 4,
id2word = tweets_dict,
passes = 10,
workers = 2)# Display topics
model.show_topics()

You can see that we are required to provide an estimate of the number of topics within our dataset, via the num_topics hyperparameter. There are, as far as I am aware, two methods of determining the optimal number of topics:

您可以看到，我們需要通過num_topics超參數(shù)來估計數(shù)據(jù)集中主題的數(shù)量。 據(jù)我所知，有兩種確定最佳主題數(shù)的方法：

Build multiple LDA models and compute their coherence score with a Coherence Model.

構(gòu)建多個LDA模型并計算其連貫性得分為 相干模型 。

Domain expertise and intuition.

領(lǐng)域?qū)I(yè)知識和直覺。

From a trading point of view, this is where domain knowledge and market expertise can help. We would expect the topics within our Twitter data, bearing in mind they are the product of financial news publications, to focus primarily on the following subjects:

從交易的角度來看，這是領(lǐng)域知識和市場專業(yè)知識可以提供幫助的地方。 考慮到它們是金融新聞出版物的產(chǎn)物，我們希望Twitter數(shù)據(jù)中的主題主要集中于以下主題：

• Copper price (naturally)

  銅價(自然)

• The U.S. / China trade war

  美中貿(mào)易戰(zhàn)

• The U.S. President Donald Trump

  美國總統(tǒng)唐納德·特朗普

• Major Copper miners

  主要銅礦商

• Macroeconomic announcements

  宏觀經(jīng)濟(jì)公告

• Local producing country civil/political unrest

  當(dāng)?shù)厣a(chǎn)國的內(nèi)亂/政治動蕩

Aside from this, one should use their own judgment when determining this hyperparameter.

除此之外，在確定此超參數(shù)時應(yīng)使用自己的判斷。

It is worth mentioning that a whole host of other hyperparameters exists. This flexibility makes Gensim’s LDA model extremely powerful. For example, as a Bayesian model, if we had ‘A-priori’ belief on a topic/word probability, our LDA model allows us to encode these priors for the Dirichlet distribution through the init_dir_prior method, or similarly through the eta hyperparameter.

值得一提的是，其他超參數(shù)整個主機(jī)的存在。 這種靈活性使Gensim的LDA模型極為強(qiáng)大。 例如，作為貝葉斯模型，如果我們對主題/單詞的概率具有“先驗(yàn)”信念，則我們的LDA模型允許我們通過init_dir_prior方法或類似地通過eta超參數(shù)為Dirichlet分布編碼這些先驗(yàn)。

Getting back to our model, you will note that we have used the multicore variant of Gensim’s LdaModelwhich allows for a faster implementation (ops are parallelized for multicore machines):

回到我們的模型，您會注意到，我們使用了Gensim的LdaModel的多核變體，該變體可以實(shí)現(xiàn)更快的實(shí)現(xiàn)(多核機(jī)器并行化操作)：

LDA Model show_topics() output: Note the topics numbered 0–4 containing the words and their associated weight i.e. how much they contribute to the topic.LDA模型show_topics()輸出：注意，編號為0–4的主題包含單詞及其關(guān)聯(lián)的權(quán)重，即它們對主題的貢獻(xiàn)程度。

A cursory inspection of the topics within our model would suggest that we have both relevant data and that our LDA model has done a reasonable job of modelling said topics.

粗略檢查模型中的主題將表明我們擁有相關(guān)數(shù)據(jù)，并且LDA模型已經(jīng)完成了對所述主題進(jìn)行建模的合理工作。

In order to understand the distribution of topics and their keywords, we will use pyLDAvis which launches an interactive widget making it ideal for use in Jupyter/Colab notebooks:

為了了解主題及其關(guān)鍵字的分布，我們將使用pyLDAvis啟動一個交互式小部件，使其非常適合在Jupyter / Colab筆記本中使用：

pyLDAvis.enable_notebook()
topic_vis = pyLDAvis.gensim.prepare(model, cbow_tweets, tweets_dict)
topic_visLDA Model — Twitter News Data, Topic Distribution.LDA模型-Twitter新聞數(shù)據(jù)，主題分布。

LDA模型結(jié)果 (LDA Model Results)

Upon inspection of the resulting topic plot, we can see that our LDA model has done a reasonable job of capturing the salient topics and their constituent words within our Twitter data.

通過查看最終的主題圖，我們可以看到我們的LDA模型在捕獲Twitter數(shù)據(jù)中的重要主題及其組成詞方面做得很合理。

What makes for a robust topic model?

是什么構(gòu)成健壯的主題模型？

A good topic model typically exhibits large, distinct topics (circles) with no overlap. The areas of said circles are proportional to the proportions of the topics across the ‘N’ total tokens in the corpus (namely, our Twitter data). The centres of each topic circle are set in two dimensions: PC1 and PC2, and the distance between them set by the output of a dimensionality reduction model (Multidimensional Scaling, to be precise) that is run on the inter-topic distance matrix. A full explanation of the mathematical detail behind the pyLDAvis topic visual can be found here.

一個好的主題模型通常表現(xiàn)出沒有重疊的大而獨(dú)特的主題(圓圈)。 所述圓圈的面積與語料庫中“ N”個總標(biāo)記中主題的比例(即我們的Twitter數(shù)據(jù))成比例。 每個主題圓的中心都設(shè)置為二維：PC1和PC2，它們之間的距離由在主題間距離矩陣上運(yùn)行的降維模型(準(zhǔn)確地說是多維縮放)的輸出設(shè)置。 pyLDAvis主題外觀背后的數(shù)學(xué)細(xì)節(jié)的完整說明可以在這里找到。

Interpreting our results

解釋我們的結(jié)果

While remembering not to lose sight of the problem that we are trying to solve, specifically, understand whether there are any useful signals in our tweet data that might affect the Copper’s spot price, we must make a qualitative assessment.

在記住不要忘記我們試圖解決的問題時，尤其是要了解我們的推文數(shù)據(jù)中是否有任何有用的信號可能會影響銅的現(xiàn)貨價格，我們必須進(jìn)行定性評估。

Examining the individual topics in detail, we can see a promising set of results, specifically top words appearing within the individual topics, that adhere largely to our expected topic criteria above:

詳細(xì)檢查各個主題，我們可以看到一系列有希望的結(jié)果，尤其是各個主題中出現(xiàn)的熱門單詞，這些結(jié)果在很大程度上符合我們上面預(yù)期的主題標(biāo)準(zhǔn)：

Topic Number:

主題編號：

Copper Mining & Copper Exporting Countries

銅礦山和銅出口國

Top words include major Copper miners (BHP Billiton, Antofagasta, Anglo American & Rio Tinto), along with mentions of major Copper exporting countries i.e. Peru, Chile, Mongolia, etc.

熱門詞包括主要的銅礦商(必和必拓，安托法加斯塔，英美資源集團(tuán)和力拓)，以及主要的銅出口國，例如秘魯，智利，蒙古等。

2. China Trade & Manufacturing Activity

2. 中國貿(mào)易與制造業(yè)活動

Top words include ‘Copper’, ‘Copper price’, ‘China’, ‘Freeport’ and ‘Shanghai’.

熱門詞包括“銅”，“銅價格”，“中國”，“自由港”和“上海”。

3. U.S. / China Trade War

3. 中美貿(mào)易戰(zhàn)

Top words include ‘Copper’, ‘Price’, ‘China’, ‘Trump’, ‘Dollar’, and the ‘Fed’, but also some unusual terms like ‘Chile’ and ‘Video’.

熱門詞包括“銅”，“價格”，“中國”，“特朗普”，“美元”和“美聯(lián)儲”，還有一些不尋常的術(shù)語，例如“智利”和“視頻”。

On the strength of the results above, we make the decision to proceed with our NLP trading strategy, on the strength that our twitter data exhibits enough information relevant to the spot price of Copper. More importantly, we can be confident of the relevancy of our Twitter data with respect to the price of Copper — the topics that our LDA Model uncovered adhered to our view of the expected topics that should be present within the data.

根據(jù)上述結(jié)果，我們決定繼續(xù)執(zhí)行NLP交易策略，因?yàn)槲覀兊腡witter數(shù)據(jù)顯示出與銅的現(xiàn)貨價格有關(guān)的足夠信息。 更重要的是，我們可以確信我們的Twitter數(shù)據(jù)的關(guān)聯(lián)性 ，相對于銅的價格-的主題，我們的LDA示范破獲堅持我們的預(yù)期主題視圖 應(yīng)該存在于數(shù)據(jù)中。

驗(yàn)證LDA模型 (Validate LDA Model)

As Data Scientists, we know that we must validate the integrity and robustness of any model. Our LDA Model is no different. We can do so by checking the Coherence (mentioned above) of our model. In layman terms, Coherence measures the relative distance between words within a topic. The mathematical detail on the mathematics behind precisely how this score is calculated can be found in this paper. I have omitted to repeat the various expressions for brevity’s sake.

作為數(shù)據(jù)科學(xué)家，我們知道我們必須驗(yàn)證任何模型的完整性和健壯性。 我們的LDA模型也不例外。 我們可以通過檢查模型的一致性(如上所述)來實(shí)現(xiàn)。 用外行術(shù)語來說，連貫性是衡量一個主題中單詞之間的相對距離。 在這一點(diǎn)上是背后正是如何計算數(shù)學(xué)的數(shù)學(xué)細(xì)節(jié)可以在本作中找到文件 。 為了簡潔起見，我省略了重復(fù)各種表達(dá)式的步驟。

Generally speaking, a score between .55 and .70 is indicative of a skillful topic model:

一般來說，.55和.70之間的得分表示熟練的主題模型：

# Compute Coherence Score
coherence_model = gs.models.CoherenceModel(
model=model,
texts=tweets_preprocessed,
dictionary=tweets_dict,
coherence='c_v')coherence_score = coherence_model.get_coherence()
print(f'Coherence Score: {coherence_score}')Calculating the Coherence Score of our LDA model, based on the confirmation measure, ‘c_v’, (as opposed to UMass).根據(jù)確認(rèn)量“ c_v”(與UMass相對)，計算我們的LDA模型的一致性得分。

At a Coherence Score of .0639, we can be reasonably confident that our LDA Model has been trained on the correct number of topics, and retains an adequate degree of semantic similarity between high scoring words in each.

在.0639的連貫分?jǐn)?shù)下，我們可以合理地確信我們的LDA模型已針對正確數(shù)量的主題進(jìn)行了訓(xùn)練，并且在每個高分單詞之間保留了足夠的語義相似度。

Our choice of score measure, observable in the signature of the above Coherence Model logic, is motivated by the results in the paper by Roder, Both & Hindeburg. You can see that we have chosen to score our model against the coherence = 'c_v measure, as opposed to ‘u_mass’, ‘c_v’, ‘c_uci’. etc. The ‘c_v’ score measure was found to return superior results to that of the other measures, particularly in cases of small word sets, qualifying our choice.

Roder，Both和Hindeburg在論文中的結(jié)果激勵了我們選擇分?jǐn)?shù)度量的方法，可以從上述一致性模型邏輯的簽名中看出 。 您可以看到我們選擇了對模型的coherence = 'c_v度量，而不是'u_mass'，'c_v'，'c_uci'。 我們發(fā)現(xiàn)，“ c_v”評分標(biāo)準(zhǔn)比其他方法能獲得更好的結(jié)果，特別是在單詞集較小的情況下，符合我們的選擇。

情感分?jǐn)?shù)：VADER (Sentiment Score: VADER)

Having been satisfied that our twitter data contains relevant enough information to potentially be predictive of short-term Copper price movements, we move onto the sentiment analysis part of our problem.

在滿意我們的推特數(shù)據(jù)包含足夠相關(guān)的信息以潛在地預(yù)測短期銅價走勢之后，我們繼續(xù)進(jìn)行情緒分析 部分 我們的問題。

We will use NLTK’s Valence Aware Dictionary and sEntiment Reasoner (VADER) to analyse our tweets, and, based on the sum of the underlying intensity of each word within each tweet, generate a sentiment score between -1 and 1.

我們將使用NLTK的價數(shù)意識字典和情感推理器(VADER)分析我們的推文，并根據(jù)每個推文中每個單詞的基本強(qiáng)度總和得出-1和1之間的情感分?jǐn)?shù)。

Irrespective of whether we employ single-tokens, ngrams, stems, or lemmas in our NLP model, fundamentally, each token in our tweet data contains some information. Possibly the most important part of this information is the word’s sentiment.

無論我們在NLP模型中采用單令牌，ngram，詞干還是引理，從根本上講，tweet數(shù)據(jù)中的每個令牌都包含一些信息。 該信息中最重要的部分可能是單詞的情感。

VADER is a popular heuristic, rule-based (composed by humans) sentiment analysis model by Hutto and Gilbert. It is particularly accurate (and was designed specifically for this application) for use on social media text. It seems rational, therefore, to use it for our project.

VADER是Hutto和Gilbert流行的啟發(fā)式，基于規(guī)則的(由人組成)情感分析模型。 它在社交媒體文本上使用特別準(zhǔn)確(并且是為此應(yīng)用程序?qū)ｉT設(shè)計的)。 因此，將其用于我們的項目似乎是合理的。

VADER’s implementation is very straightforward:

VADER的實(shí)現(xiàn)非常簡單：

# Instantiate SIA class
analyser = SentimentIntensityAnalyzer()sentiment_score = []for tweet in tweets_df[‘text’]:
sentiment_score.append(analyser.polarity_scores(tweet))

The SentimentIntensityAnalyzer contains a dictionary of tokens and their individual scores. We then generate a sentiment score for each tweet in our tweets DataFrame and access the result, a dictionary object, of the four separate score components generated by the VADER model:

SentimentIntensityAnalyzer包含一個令牌及其各個分?jǐn)?shù)的字典。 然后，我們在tweet DataFrame中為每個tweet生成一個情緒得分，并訪問由VADER模型生成的四個獨(dú)立得分成分的結(jié)果(字典對象)：

• The negative proportion of the text
  文字的負(fù)比例
• The positive proportion of the text
  文字的正比例
• The neutral proportion of the text &
  文字的中性比例＆
• The combined intensity of sentiment polarity in the above, the ‘Compound’ score
  情緒極性的綜合強(qiáng)度，即“復(fù)合”得分

#@title Extract Sentiment Score Elementssentiment_prop_negative = []
sentiment_prop_positive = []
sentiment_prop_neutral = []
sentiment_score_compound = []for item in sentiment_score:
sentiment_prop_negative.append(item['neg'])
sentiment_prop_positive.append(item['neu'])
sentiment_prop_neutral.append(item['pos'])
sentiment_score_compound.append(item['compound'])# Append to tweets DataFrame
tweets_df['sentiment_prop_negative'] = sentiment_prop_negative
tweets_df['sentiment_prop_positive'] = sentiment_prop_positive
tweets_df['sentiment_prop_neutral'] = sentiment_prop_neutral
tweets_df['sentiment_score_compound'] = sentiment_score_compoundTweet Data Sentiment Scores: Negative, Positive, and Compound, Daily.Tweet數(shù)據(jù)情感評分：負(fù)面，正面和復(fù)合，每日。

After plotting the rolling scores for the various components, negative, positive, and compound scores (we leave neutral out), we can make a few observations:

在繪制出各個組成部分的消極得分，消極得分，積極得分和綜合得分的滾動得分之后(我們將中性得分排除在外)，我們可以進(jìn)行一些觀察：

• Clearly, the sentiment score is very noisy/volatile — our Twitter data may simply contain redundant information, with a few causing large spikes in scores. This is, however, the nature of signal finding — we only need that one piece of salient information.
  顯然，情緒得分非常嘈雜/不穩(wěn)定-我們的Twitter數(shù)據(jù)可能只包含冗余信息，有一些會導(dǎo)致得分大幅度上升。 但是，這就是發(fā)現(xiàn)信號的本質(zhì)-我們只需要一條重要信息。
• Our Twitter data appears to be predominantly positive: the mean negative score is .09, whilst the mean positive score is .83.
  我們的Twitter數(shù)據(jù)似乎主要是正面的：平均負(fù)面分?jǐn)?shù)是.09，而平均正面分?jǐn)?shù)是.83。

情緒比分VS銅現(xiàn)貨價格 (Sentiment Score VS Copper Spot Price)

Now we must evaluate whether our hard work has paid off: Is our sentiment score predictive of Copper’s spot price!

現(xiàn)在，我們必須評估我們的辛勤工作是否取得了回報： 我們的情緒得分是否可以預(yù)測銅的現(xiàn)貨價格！

On first glance, there does not appear to be any association between the spot price and our compound score:

乍一看，現(xiàn)貨價格與我們的綜合評分之間似乎沒有任何關(guān)聯(lián)：

Compound Sentiment Score vs Spot Copper ($/Mt), Daily.每日綜合情緒指數(shù)與現(xiàn)貨銅價格(美元/噸)。

However, when we apply a classic smoothing technique and calculate the rolling average of our sentiment score, we see a different picture emerge:

但是，當(dāng)我們應(yīng)用經(jīng)典的平滑技術(shù)并計算情緒得分的滾動平均值時，我們看到了另一幅圖：

Rolling 21d Mean Compound Sentiment Score vs Spot Copper ($/mt), Daily.每日21天復(fù)合平均情緒指數(shù)與現(xiàn)貨銅($ / mt)的對比。

This now looks a lot more promising. With the exception of the time period between January and August 2017, we can readily observe a near-symmetric, inverse relationship between our 21-day rolling mean compound score and the spot price of Copper.

現(xiàn)在，這看起來很多更有前途。 除了2017年1月至2017年8月這段時間之外，我們可以很容易地觀察到我們21天滾動平均復(fù)合得分與銅的現(xiàn)貨價格之間的近似對稱，反比關(guān)系。

結(jié)論 (Conclusion)

At this juncture, we pause to consider the options available to us on how we want our model to process and classify the underlying sentiment within a piece of text data, and, critically, how the model will act on this classification in terms of its trading decisions.

在此關(guān)頭，我們暫停考慮可供我們選擇的方案，這些方案涉及我們希望模型如何處理和分類文本數(shù)據(jù)中的潛在情緒，以及至關(guān)重要的是，模型將如何根據(jù)其交易對這種分類采取行動決定。

Consistent with the Occam’s Razor principle, we implemented an out-of-the-box solution to analyse the underlying sentiment within our twitter data. As well as exploring some renowned EDA and preprocessing techniques as a prerequisite, we used NLTK’s Valence Aware Dictionary and sEntiment Reasoner (VADER), to generate an associated sentiment score for each tweet, and examined the correlation of said score against simple corresponding Copper spot price movements.

與Occam的Razor原則一致，我們實(shí)施了一種即用型解決方案來分析Twitter數(shù)據(jù)中的基本情緒。 除了探索一些著名的EDA和預(yù)處理技術(shù)作為先決條件外，我們還使用了NLTK的價數(shù)感知字典和情感推理器( VADER )來生成每個推文的相關(guān)情感評分，并檢查了該評分與簡單的相應(yīng)銅現(xiàn)貨價格的相關(guān)性。動作。

Interestingly a correlation was observed between our rolling compound sentiment score and the price of Copper. This does not, of course, imply causation. Moreover, it may simply be the news data trails that of the price of Copper, and our tweet data is simply reporting on its movements. Nonetheless, there is scope for further work.

有趣的是，我們的滾動復(fù)合情緒評分與銅價之間存在相關(guān)性。 當(dāng)然，這并不意味著因果關(guān)系。 此外，新聞數(shù)據(jù)可能僅落后于銅價，而我們的推特數(shù)據(jù)僅是在報道其走勢。 盡管如此，仍有進(jìn)一步工作的余地。

觀察，批評和進(jìn)一步分析 (Observations, Criticisms & Further Analysis)

In reality, the design of a systematic trading strategy necessitates a great deal more mathematical and analytical rigour, as well as a good dose of domain expertise. One would typically invest a great deal of time designing a suitable label that best encompasses the signal and the magnitude of the price movement (if at all!) found within said signal, notwithstanding a thorough investigation of the signal itself.

實(shí)際上，系統(tǒng)交易策略的設(shè)計需要更多的數(shù)學(xué)和分析嚴(yán)格性，以及大量的領(lǐng)域?qū)I(yè)知識。 盡管會仔細(xì)研究信號本身，但通常會花費(fèi)大量時間來設(shè)計合適的標(biāo)簽，以最好地包含信號和在所述信號中發(fā)現(xiàn)的價格變動幅度(如果有的話！)。

Scope for very interesting further work and analysis exists in abundance with respect to our problem:

關(guān)于我們的問題，存在很多非常有趣的進(jìn)一步工作和分析的范圍：

Neural Network Embeddings: As an example, in order to intimately understand how an NLP model, with an associated label (or labels), makes a trading decision we would look to train a Neural Network with an Embedding Layer. We could then examine the trained embedding layer to understand how the model treats the various tokens within the layer against those with a similar encoding, and the label(s). We could then visualise how the model groups words with respect to their effect on the class we wish to predict i.e. 0 for negative price movement, 1 for positive price movement. TensorFlow’s Embedding Projector, for example, is an invaluable tool for visualising such embeddings:

神經(jīng)網(wǎng)絡(luò)嵌入：例如，為了深入了解帶有關(guān)聯(lián)標(biāo)簽的NLP模型如何做出交易決策，我們希望訓(xùn)練一個具有嵌入層的神經(jīng)網(wǎng)絡(luò)。 然后，我們可以檢查經(jīng)過訓(xùn)練的嵌入層，以了解該模型如何將層中的各種標(biāo)記與具有相似編碼的標(biāo)記和標(biāo)簽進(jìn)行比較。 然后，我們可以可視化模型如何根據(jù)單詞對我們希望預(yù)測的類別的影響來對單詞進(jìn)行分組，即0表示負(fù)價格變動，1表示正價格變動。 例如，TensorFlow的Embedding Projector是一種使此類嵌入可視化的寶貴工具：

2. Multinomial Naive Bayes

2.多項式樸素貝葉斯

We used VADER to parse and interpret the underlying sentiment of our Twitter data, which it did a reasonable job of doing. The drawback of using VADER, however, is that it doesn’t consider all the words in a document, only about 7,500 in fact. Given the complexity of commodity trading and its associated terminology, we might be missing crucial information.

我們使用VADER來分析和解釋我們Twitter數(shù)據(jù)的基本情感，這是一項合理的工作。 但是，使用VADER的缺點(diǎn)是它沒有考慮文檔中的所有單詞，實(shí)際上僅考慮了大約7500個單詞。 鑒于商品交易及其相關(guān)術(shù)語的復(fù)雜性，我們可能會丟失重要信息。

As an alternative, we could employ a Naive Bayes classifier to find sets of keywords that are predictive of our target, be it the price of Copper itself or a sentiment score.

作為替代方案，我們可以使用樸素貝葉斯分類器來找到可以預(yù)測目標(biāo)的關(guān)鍵字集，無論是銅本身的價格還是情緒得分。

3. Intra-day Data

3 。 日內(nèi)數(shù)據(jù)

Intra-day data in nearly all cases is a must when designing an NLP trading strategy model, for the reasons mentioned in the introduction. Time and trade execution is very much of the essence when attempting to capitalise on news/event-based price movements.

出于導(dǎo)言中提到的原因，在設(shè)計NLP交易策略模型時，幾乎所有情況下的日內(nèi)數(shù)據(jù)都是必需的。 當(dāng)試圖利用基于新聞/事件的價格變動時，時間和交易執(zhí)行是非常重要的。

Thank you for taking the time to read my article, I hope you found it interesting.

感謝您抽出寶貴的時間閱讀我的文章，希望您覺得它有趣。

Please do feel free to reach out — I very much welcome comments & constructive critiques.

請隨時與我們聯(lián)系-我非常歡迎您提出評論和提出建設(shè)性的批評。

翻譯自: https://towardsdatascience.com/spot-vs-sentiment-nlp-sentiment-scoring-in-the-spot-copper-market-492456b031b0

電力現(xiàn)貨市場現(xiàn)貨需求

總結(jié)

以上是生活随笔為你收集整理的电力现货市场现货需求_现货与情绪：现货铜市场中的自然语言处理与情绪评分的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。