Roland Jeannier rtjeannier

## S3 File Download and Decryption Function
import boto3
import os
from botocore.exceptions import ClientError
from cryptography.fernet import Fernet
from typing import Tuple, List

def create_s3_client():
    """Create and return an S3 client."""
    return boto3.client('s3')

## df_cleaner.py
def clean_dataframe_columns(df):
    df.columns = column_cleaner(df.columns)

# Takes a dataframe and cleans all the column names
def column_cleaner(columns):
    clean_list = []
    for c in columns:
        c = clean_column(c)
        clean_list.append(create_unique_name(c, clean_list))
    return clean_list

## checkversion.py
import sklearn

print('The scikit-learn version is {}.'.format(sklearn.__version__))

## recurisve_tree.py
def num_nodes(n):
    return 2**(n) - 1

def parent_of_value(value, tree):
    for n in tree:

        if n.value == value:
            if n.parent != None:
                return n.parent.value
            else:

## gist:49a27e5886669445673c3735da251c7a
# making file *.csv gets rid of all csvs
git filter-branch --index-filter 'git rm -r --cached --ignore-unmatch <file/dir>' HEAD

# THIS IS DANGEROUS. WILL BREAK EVERYTHING. But it works if you are okay with that...

## calculate_feature_importance.py
from sklearn.ensemble import BaggingClassifier

dtc_params = {
    'max_features': [0.5, 0.7, 1.0],
    'max_samples': [0.5, 0.7, 1.0],
    'n_estimators': [2, 5, 10, 20],
}

dtc_gs = GridSearchCV(BaggingClassifier(), dtc_params, cv=5, verbose=1)
dtc_gs.fit(X, y)

## baggingClassifer.py

from sklearn.ensemble import BaggingClassifier
from sklearn.ensemble import RandomForestClassifier


bc_params = {"base_estimator__max_depth": [3,5,10,20],
          "base_estimator__max_features": [None, "auto"],
          "base_estimator__min_samples_leaf": [1, 3, 5, 7, 10],
          "base_estimator__min_samples_split": [2, 5, 7],
          'bootstrap_features': [False, True],

## scraper_start.py
import requests
import bs4
from bs4 import BeautifulSoup
import time
import numpy as np
import pandas as pd
import time
from selenium.webdriver.chrome.options import Options
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException

## feature_importance_corr.py
from sklearn.ensemble import ExtraTreesClassifier
plt.style.use('fivethirtyeight')

def feature_importance_eda(X, y):

    '''Get an estimate of the feature importance of data'''

    # Build a forest and compute the feature importances
    forest = ExtraTreesClassifier(n_estimators=250,
                                  random_state=0)

## terrorist_plot.html


<!DOCTYPE html>
<html lang="en">
    <head>
        <meta charset="utf-8">
        <title>Bokeh Plot</title>

<link rel="stylesheet" href="https://cdn.pydata.org/bokeh/release/bokeh-0.12.5.min.css" type="text/css" />
	import boto3
	import os
	from botocore.exceptions import ClientError
	from cryptography.fernet import Fernet
	from typing import Tuple, List

	def create_s3_client():
	"""Create and return an S3 client."""
	return boto3.client('s3')
	def clean_dataframe_columns(df):
	df.columns = column_cleaner(df.columns)

	# Takes a dataframe and cleans all the column names
	def column_cleaner(columns):
	clean_list = []
	for c in columns:
	c = clean_column(c)
	clean_list.append(create_unique_name(c, clean_list))
	return clean_list
	import sklearn

	print('The scikit-learn version is {}.'.format(sklearn.__version__))
	def num_nodes(n):
	return 2**(n) - 1

	def parent_of_value(value, tree):
	for n in tree:

	if n.value == value:
	if n.parent != None:
	return n.parent.value
	else:
	# making file *.csv gets rid of all csvs
	git filter-branch --index-filter 'git rm -r --cached --ignore-unmatch <file/dir>' HEAD

	# THIS IS DANGEROUS. WILL BREAK EVERYTHING. But it works if you are okay with that...
	from sklearn.ensemble import BaggingClassifier

	dtc_params = {
	'max_features': [0.5, 0.7, 1.0],
	'max_samples': [0.5, 0.7, 1.0],
	'n_estimators': [2, 5, 10, 20],
	}

	dtc_gs = GridSearchCV(BaggingClassifier(), dtc_params, cv=5, verbose=1)
	dtc_gs.fit(X, y)

	from sklearn.ensemble import BaggingClassifier
	from sklearn.ensemble import RandomForestClassifier


	bc_params = {"base_estimator__max_depth": [3,5,10,20],
	"base_estimator__max_features": [None, "auto"],
	"base_estimator__min_samples_leaf": [1, 3, 5, 7, 10],
	"base_estimator__min_samples_split": [2, 5, 7],
	'bootstrap_features': [False, True],
	import requests
	import bs4
	from bs4 import BeautifulSoup
	import time
	import numpy as np
	import pandas as pd
	import time
	from selenium.webdriver.chrome.options import Options
	from selenium import webdriver
	from selenium.common.exceptions import NoSuchElementException
	from sklearn.ensemble import ExtraTreesClassifier
	plt.style.use('fivethirtyeight')

	def feature_importance_eda(X, y):

	'''Get an estimate of the feature importance of data'''

	# Build a forest and compute the feature importances
	forest = ExtraTreesClassifier(n_estimators=250,
	random_state=0)


	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="utf-8">
	<title>Bokeh Plot</title>

	<link rel="stylesheet" href="https://cdn.pydata.org/bokeh/release/bokeh-0.12.5.min.css" type="text/css" />