tugloo1

df['date_info'] = pd.to_datetime(df['year'] + ' ' + df['periodName'], format="%Y %B")
df['num_of_employees'] = pd.to_numeric(df['value'])
df = df.drop('footnotes', 1)
df = df.drop('period', 1)
df = df.drop('periodName', 1)
df = df.drop('value', 1)
df = df.drop('year', 1)

df.plot(x='date_info', y='num_of_employees')

tugloo1

import arrow
import pprint
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import requests
from matplotlib.axes import Axes


def get_bls_key():
    """

tugloo1

import requests
import pandas as pd
import matplotlib.pyplot as plt



def get_bls_key():
    """
    This method will get the BLS API key that is expected in api-key.txt file. That file is in the .gitignore and
    each user should have their own API key

tugloo1

/System/Library/Frameworks/Python.framework/Versions/2.7/bin/python2.7 /Applications/PyCharmOld.app/Contents/helpers/pydev/pydevd.py --multiproc --qt-support --client 127.0.0.1 --port 54837 --file /Users/piyushgupta/projects/udacityintroML/final_project/poi_id.py
pydev debugger: process 6180 is connecting

Connected to pydev debugger (build 143.2371)
/Library/Python/2.7/site-packages/sklearn/cross_validation.py:41: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
  "This module will be removed in 0.20.", DeprecationWarning)
total number of data points:  146
total number of people in dataset:  146
total number of poi:  18
total number of not poi:  128

tugloo1

import sys
from datetime import date
import quandl

'''sys.argv is a module that has all the inputs of a command line in a list
so for example if you run

python main.py "2018-1-25"
sys.argv would be [main.py', '2018-1-25']

tugloo1

selk = SelectKBest(k=5)
dtc = DecisionTreeClassifier(max_depth=6, random_state=42, min_samples_split=3)

pipline_steps = [
	('best_feature', selk),
	('decision_tree', dtc)
]

clf = Pipeline(pipline_steps)

tugloo1

from pandas import DataFrame, Series

a = [1, 2, 3, 4]
b = a.append(5)

print(a)
# [1, 2, 3, 4, 5]
print(b)
# None

tugloo1

if obs_mean < null_mean:
  pval = 2 * (null_vals < obs_mean).mean()
else:
  pval = 2 * (null_vals > obs_mean).mean()
pval

tugloo1

def calculate_path_weight(node, seen_nodes, current_weight):
    # Case when we've seen all the nodes
    if set(seen_nodes) == set(input_graph.keys()):
        return current_weight
    to_return_path_weight = 10000
    for path_node, path_weight in input_graph[node]:
        if path_node not in seen_nodes:
            new_seen_nodes = seen_nodes + [path_node]
            total_path_weight = calculate_path_weight(path_node, new_seen_nodes, current_weight + path_weight)
            if total_path_weight < to_return_path_weight:

tugloo1

def get_nodes_parent(tree, node_to_evaluate):
    for i, row in enumerate(tree):
        if row[node_to_evaluate] == 1:
            return i
    else:
        return None