conormm

                                                  text                                              title                        paper  automated_readability_index  coleman_liau_index  flesch_kincaid_grade_level  flesch_readability_ease  gunning_fog_index  n_chars  n_polysyllable_words  n_sents  n_syllables  n_unique_words  n_words  smog_index
0    four us states are suing the trump administrat...  Four states sue Trump administration over 'un-...  https://www.theguardian.com                    58.698156           15.299608                   46.986883               -45.888247          51.064935     4108                   136        7         1284             365      770   28.309659
1    sean spicer, the press secretary for the trump...  Sean Spicer holds first Trump administration p...  https://www.theguardian.com                    18.558549           15.390357                   15.867059                31.768431          17.921569      466                    14        3          147              66       

conormm

articles = get_articles(the_guardian, breitbart, title_topic="Trump")
articles["text"] = articles.text.map(clean_text)
articles["text"] = preprocess_articles(articles.text)

def get_readability_stats(parsed_articles):

    stats_list = []
    for ix, article in enumerate(parsed_articles):
        doc = tcy.Doc(article)
        readability_stats = tcy.text_stats.readability_stats(doc)

conormm

library(readxl)
library(janitor)
library(ggraph)
library(igraph)

df <- readxl::read_excel("/eurovision_song_contest_1975_2016.xlsx") %>% 
  clean_names()

df <- df[, c(5, 6, 1:4, 7)]

conormm

import numpy as np
import spacy
from sklearn.decomposition import PCA

nlp = spacy.load("en")

animals = "dog cat hamster lion tiger elephant cheetah monkey gorilla antelope rabbit mouse rat zoo home pet fluffy wild domesticated"

animal_tokens = nlp(animals)
animal_vectors = np.vstack([word.vector for word in animal_tokens if word.has_vector])

conormm

library(readr)
library(dplyr)
library(ggplot2)
library(janitor)
library(broom)
library(lubridate)

# available at https://www.kaggle.com/berkeleyearth/climate-change-earth-surface-temperature-data
temp_loc <- "/Users/conormcdonald/Downloads/GlobalLandTemperatures/GlobalLandTemperaturesByCountry.csv"

conormm

imdb_score_summary <- df %>% 
  summarise_each(funs(min, max, mean, median, sd), imdb_score) %>% 
  gather(stat, value) 
  
df %>% 
  ggplot(aes(imdb_score)) + 
  geom_histogram(bins = 50, colour = "black", fill = "red", alpha = 0.4) +
  theme_minimal() +
  annotation_custom(tableGrob(imdb_score_summary, rows = NULL), 
                    xmin = 2.5, 

conormm

library(tidyverse)
library(here)
library(broom)
library(corrr)
library(forcats)
library(stringr)
library(lubridate)
library(gridExtra)

df <- read_csv("movie_metadata.csv")

conormm

df %>% map_df(~sum(is.na(.))) %>% glimpse()

Observations: 1
Variables: 28
$ color                     <int> 19
$ director_name             <int> 104
$ num_critic_for_reviews    <int> 50
$ duration                  <int> 15
$ director_facebook_likes   <int> 104
$ actor_3_facebook_likes    <int> 23

conormm

num_df <- num_df %>% 
  mutate(years_since_release = 2017 - title_year) %>% 
  select(-title_year)

conormm

df %>% 
  group_by(title_year) %>% 
  summarise(mean_rating = mean(imdb_score), 
            upper_rating = quantile(imdb_score, 0.975), 
            lower_rating = quantile(imdb_score, 0.0275)) %>% 
  ggplot(aes(title_year, mean_rating)) +
  geom_line(colour = "dodger blue") + 
  geom_point(alpha = 0.5) + 
  geom_smooth(method = "lm", colour = "red", alpha = 0.6, se = FALSE) +
  geom_errorbar(aes(ymin = upper_rating, ymax = lower_rating)) +