emmagrimaldi

from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline


steps = [
    ("vectorizer", TfidfVectorizer(stop_words=my_stopwords)),
    ("rf", RandomForestClassifier())
]

# instatiating the pipeline

emmagrimaldi

import pandas as pd
from rake_nltk import Rake
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
from sklearn.feature_extraction.text import CountVectorizer

df = pd.read_csv('https://query.data.world/s/uikepcpffyo2nhig52xxeevdialfl7')

df = df[['Title','Genre','Director','Actors','Plot']]
df.head()

emmagrimaldi

# initializing the new column
df['Key_words'] = ""

for index, row in df.iterrows():
    plot = row['Plot']
    
    # instantiating Rake, by default it uses english stopwords from NLTK
    # and discards all puntuation characters as well
    r = Rake()

emmagrimaldi

# instantiating and generating the count matrix
count = CountVectorizer()
count_matrix = count.fit_transform(df['bag_of_words'])

# generating the cosine similarity matrix
cosine_sim = cosine_similarity(count_matrix, count_matrix)

emmagrimaldi

# creating a Series for the movie titles so they are associated to an ordered numerical
# list I will use in the function to match the indexes
indices = pd.Series(df.index)

#  defining the function that takes in movie title 
# as input and returns the top 10 recommended movies
def recommendations(title, cosine_sim = cosine_sim):
    
    # initializing the empty list of recommended movies
    recommended_movies = []

emmagrimaldi

data = []
for event in event_types:
    event_data = dict(
            lat = df.loc[df['EVENT_TYPE'] == event,'BEGIN_LAT'],
            lon = df.loc[df['EVENT_TYPE'] == event,'BEGIN_LON'],
            name = event,
            marker = dict(size = 8, opacity = 0.5),
            type = 'scattermapbox'
        )
    data.append(event_data)

emmagrimaldi

annotations = [dict(
  
              # text I want to display. I used <br> to break it into two lines
              text = 'All US storm events that caused more than $50k of economic damage,<br> from 2000 until today', 
              
              # font and border characteristics
              font = dict(color = '#FFFFFF', size = 14), borderpad = 10, 
              
              # positional arguments
              x = 0.05, y = 0.05, xref = 'paper', yref = 'paper', align = 'left', 

emmagrimaldi

layout = dict(
    height = 800,
    # top, bottom, left and right margins
    margin = dict(t = 0, b = 0, l = 0, r = 0),
    font = dict(color = '#FFFFFF', size = 11),
    paper_bgcolor = '#000000',
    mapbox = dict(
        # here you need the token from Mapbox
        accesstoken = mapbox_access_token,
        bearing = 0,

emmagrimaldi

updatemenus=list([
    # drop-down 1: map styles menu
    # buttons containes as many dictionaries as many alternative map styles I want to offer
    dict(
        buttons=list([
            dict(
                args=['mapbox.style', 'dark'],
                label='Dark',
                method='relayout'
            ),                    

emmagrimaldi

{
	"folder_title": "Cookiecutter Example",
	"notebook_title": "Generate dataframe with random integer entries and calculate ",
	"n_columns": 5,
	"n_rows": 10,
  "min_value_in_df": 0,
  "max_value_in_df": 100,
	"numpy_function_to_calculate": "mean",
  "calculate_over_rows_or_columns": "columns",
	"file_name": "results",