sevperez

s = [1, 2, 3, 4, 5]
def foo(l, bar):
    return list(map(bar, l))

print(foo(s, lambda x: x * 2))      # [2, 4, 6, 8, 10]

sevperez

# What is the sentiment surrounding each character?
def sentiment_descriptor_to_val(descriptor):
    """
    - Parameters: descriptor ("negative", "neutral", or "positive")
    - Returns: -1 for "negative", 0 for "neutral", 1 for "positive"
    """
    if descriptor == "negative":
        return -1
    elif descriptor == "neutral":
        return 0

sevperez

# Which characters appear most frequently?
def frequency_count(df, col, limit=10):
    return df[col].value_counts().head(limit)

frequency_count(characters, "text")

# Ahab          474
# Stubb         224
# Queequeg      184
# Starbuck      140

sevperez

def num_unique_items(df, col):
    return len(df[col].unique())

num_unique_items(characters, "text")

# 699

sevperez

# select person entities
def select_person_entities(doc):
    return [ent for ent in doc.entities if ent.type == "PERSON"]

def person_df(doc):
    """
    - Parameters: doc (a Stanza Document object)
    - Returns: A Pandas DataFrame with one row for each entity in doc
      that has a "PERSON" type, and and columns text, type, start_char, 
      and the sentiment of the sentence in which the entity appears.

sevperez

# load the full text and put it through the pipeline
def load_text_doc(file_path):
    with open(file_path) as f:
        txt = f.read()
    return txt

moby_path = "moby_dick.txt"
moby_dick_text = load_text_doc(moby_path)
moby_dick = nlp(moby_dick_text)

sevperez

def sentiment_descriptor(sentence):
    """
    - Parameters: sentence (a Stanza Sentence object)
    - Returns: A string descriptor for the sentiment value of sentence.
    """
    sentiment_value = sentence.sentiment
    if (sentiment_value == 0):
        return "negative"
    elif (sentiment_value == 1):
        return "neutral"

sevperez

def print_entity_info(entity):
    print(f"Text:\t{entity.text}")
    print(f"Type:\t{entity.type}")
    print(f"Start:\t{entity.start_char}")
    print(f"End:\t{entity.end_char}")

print_entity_info(moby_p1.entities[0])

# Text:     Ishmael
# Type:     PERSON

sevperez

def print_word_info(word):
    print(f"Text:\t{word.text}")
    print(f"Lemma: \t{word.lemma}")
    print(f"UPOS: \t{word.upos}")
    print(f"XPOS: \t{word.xpos}")

print_word_info(moby_p1.sentences[3].words[4])

# Text:     growing
# Lemma:    grow

sevperez

def print_token_info(token):
    print(f"Text:\t{token.text}")
    print(f"Start:\t{token.start_char}")
    print(f"End:\t{token.end_char}")

print_token_info(moby_p1.sentences[0].tokens[2])

# Text:     Ishmael
# Start:    8
# End:      15