josht-jpg

trait LinearAlg<T>
where
    T: Add + Sub,
{
    fn dot(&self, w: &[T]) -> T;

    fn subtract(&self, w: &[T]) -> Vec<T>;

    fn sum_of_squares(&self) -> T;

josht-jpg

const SAFE_URL_PATTERN = /^(?:(?:https?|mailto|ftp|tel|file|sms):|[^&:/?#]*(?:[/?#]|$))/gi;

/** A pattern that matches safe data URLs. It only matches image, video, and audio types. */
const DATA_URL_PATTERN = /^data:(?:image\/(?:bmp|gif|jpeg|jpg|png|tiff|webp)|video\/(?:mpeg|mp4|ogg|webm)|audio\/(?:mp3|oga|ogg|opus));base64,[a-z0-9+\/]+=*$/i;

function _sanitizeUrl(url: string): string {
  url = String(url);
  if (url === "null" || url.length === 0 || url === "about:blank") return "about:blank";
  if (url.match(SAFE_URL_PATTERN) || url.match(DATA_URL_PATTERN)) return url;

josht-jpg

def predict_sentences(book, stop_words):
    #Break up book into sentences
    book_sentences = pd.DataFrame(book.split("."), columns = ['sentence'])
    
    #Clean sentences
    book_sentences['sentence'] = book_sentences['sentence'].\
        apply(lambda x: clean_labelled(x, stop_words))
    
    book_sentences = book_sentences[book_sentences['sentence'].\
                                    str.len() > 0] 

josht-jpg

def clean_labelled(sentence, stop_words):
    sentence = sentence.lower()
    sentence_tokens_clean = nltk.tokenize.RegexpTokenizer(r'\w+').\
                                                tokenize(sentence)
    
    sentence_clean = pd.DataFrame(sentence_tokens_clean, columns = ['word'])
    sentence_clean = [w for w in sentence_tokens_clean \
                      if w not in stop_words] 

    return sentence_clean

josht-jpg

labelled_train = pd.read_csv("labelled_train.csv")
labelled_train.columns = ['line', 'sentence', 'score']

labelled_train = pd.read_csv("labelled_test.csv")
labelled_test.columns = ['line', 'sentence', 'score']

josht-jpg

books_raw = pd.Series(books_raw)

books = books_raw.apply(get_book_contents)

books_bigrams = books.apply(bigram)

books_afinn = books_bigrams.apply(afinn_context)

books_means = books_afinn.apply(lambda x: x['score'].mean())

josht-jpg

#List the the raw contents of each book
#Each element is a string

books_raw = [owl_creek_bridge_raw,
            portrait_of_a_lady_raw,
            white_company_raw,
            ladies_paradise_raw,
            private_memoirs_raw,
            master_of_ballantrae_raw,
            agathas_husband_raw,

josht-jpg

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
sns.set(style="darkgrid")

josht-jpg

def plot_nrc(df, title):
    i = 0
    j = 0
    scores = pd.DataFrame(np.zeros((df.shape[0] // 750, 10)), columns = NRC_sentiments)

    while i < df.shape[0] - 750:
        scores.iloc[j] = df.loc[i:i + 750, 'anger':'trust'].sum()
        i += 750
        j += 1
    

josht-jpg

def plot_afinn(df, title):
    i = 0
    scores = []
    while i < df.shape[0] - 500:
        scores.append(df.iloc[i:i + 500].loc[:, 'score'].sum())
        i += 500
        
    plt.plot(scores, c=np.random.rand(3,))
    plt.ylabel("AFINN score")
    plt.title(title)