minesh1291

How to write a reproducible example.

You are most likely to get good help with your R problem if you provide a reproducible example. A reproducible example allows someone else to recreate your problem by just copying and pasting R code.

There are four things you need to include to make your example reproducible: required packages, data, code, and a description of your R environment.

• Packages should be loaded at the top of the script, so it's easy to see which ones the example needs.

• The easiest way to include data in an email is to use dput() to generate

minesh1291

"""
A weighted version of categorical_crossentropy for keras (2.0.6). This lets you apply a weight to unbalanced classes.
@url: https://gist.github.com/wassname/ce364fddfc8a025bfab4348cf5de852d
@author: wassname
"""
from keras import backend as K
def weighted_categorical_crossentropy(weights):
    """
    A weighted version of keras.objectives.categorical_crossentropy
    

minesh1291

import nltk
import gensim

text = requests.get('http://rare-technologies.com/the_matrix_synopsis.txt').text

gensim_summary = gensim.summarization.summarize(text)

minesh1291

"""
  First install text_summarizer using
  pip install git+https://github.com/lambdaofgod/text-summarizer
"""

import nltk
import text_summarizer

# prepare nltk data
nltk.download('punkt')

minesh1291

#!/usr/bin/env python
# coding: utf-8

from nltk.corpus import stopwords
from nltk.cluster.util import cosine_distance
import numpy as np
import networkx as nx
 
def read_article(file_name):
    file = open(file_name, "r")

minesh1291

minesh1291

minesh1291

from allennlp.predictors.predictor import Predictor as AllenNLPPredictor

class Predictor:
    def __init__(self, config):
        self.predictor = AllenNLPPredictor.from_path(
            "https://storage.googleapis.com/allennlp-public-models/bidaf-elmo-model-2018.11.30-charpad.tar.gz"
        )

    def predict(self, payload):
        prediction = self.predictor.predict(

minesh1291

class XGBQuantile(XGBRegressor):
  def __init__(self,quant_alpha=0.95,quant_delta = 1.0,quant_thres=1.0,quant_var =1.0,base_score=0.5, booster='gbtree', colsample_bylevel=1,
                colsample_bytree=1, gamma=0, learning_rate=0.1, max_delta_step=0,max_depth=3, min_child_weight=1, missing=None, n_estimators=100,
                n_jobs=1, nthread=None, objective='reg:linear', random_state=0,reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=None,silent=True, subsample=1):
    self.quant_alpha = quant_alpha
    self.quant_delta = quant_delta
    self.quant_thres = quant_thres
    self.quant_var = quant_var
    
    super().__init__(base_score=base_score, booster=booster, colsample_bylevel=colsample_bylevel,

minesh1291

# My version of the code at this blog post:
# https://towardsdatascience.com/automl-a-tool-to-improve-your-workflow-1a132248371f

import h2o
from h2o.automl import H2OAutoML

h2o.init()

train = h2o.import_file("https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data")
y = "C1" #e = edible, p = poisonous