#!/usr/bin/python

import sys

import pickle

sys.path.append("../tools/")

from feature_format import featureFormat, targetFeatureSplit

from tester import dump_classifier_and_data

from collections import defaultdict

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

from sklearn import linear_model as lm

from sklearn.cross_validation import train_test_split

from sklearn.cluster import KMeans

from sklearn.metrics import accuracy_score,precision_score,recall_score,f1_score,r2_score

from sklearn.svm import SVC

from sklearn.naive_bayes import GaussianNB

from sklearn import tree

from time import time

from sklearn.grid_search import GridSearchCV

from sklearn.cross_validation import StratifiedShuffleSplit

import sklearn.neighbors as KN

import sklearn.ensemble as ensem

from sklearn.feature_selection import SelectPercentile,SelectKBest,f_classif

from sklearn.pipeline import Pipeline

from sklearn import decomposition,preprocessing

from tester import test_classifier

import sklearn.neighbors as KN

from sklearn.ensemble import AdaBoostClassifier

'''

pca=PCA(n_components=2)

pca.fit(data)

return pca

print pca.explained_variance_ratio_

first_pc=pca.components_[0]

second_pc=pca.components_[1]

transfomred_data=pca.transform(data)

'''

def QueryDataSet(my_dataset):

print df.sort('Missing Vals',ascending=0)

def PlotData(target,features,Title):

plt.show()

def DrawClusters(pred, features, poi, Title,name="image.png", f1_name="feature 1", f2_name="feature 2",):

plt.show()

def Plot_n_Clustoids_AfterScaling(poi,finance_features):

DrawClusters(pred, rescaled_features, poi,'Clusters After Scaling', name="clusters_after_scaling.pdf", f1_name='salary', f2_name='exercised_stock_options')

### Load the dictionary containing the dataset

### Task 1: Select what features you'll use.

### Task 2: Remove outliers

def PlotReg(data_dict,Title):

PlotData(target,features,Title)

def RmOutliers(data_dict):

data_dict.pop('TOTAL')

return data_dict

### Task 3: Create new feature(s)

def computeFraction( poi_messages, all_messages ):

return fraction

#'from_poi_to_this_person'

#'to_messages'

#'from_this_person_to_poi'

#"from_messages"

def AddFeatures(my_dataset):

return my_dataset

def ShowCorrel(my_dataset):

CorTab.to_csv('CorrTable.csv')

### features_list is a list of strings, each of which is a feature name.

### The first feature must be "poi".

### Task 4: Try a varity of classifiers

### Please name your classifier clf for easy export below.

### Note that if you want to do PCA or other multi-stage operations,

### you'll need to use Pipelines. For more info:

### http://scikit-learn.org/stable/modules/pipeline.html

# Provided to give you a starting point. Try a variety of classifiers.

#Decent Results

#########################################################

### Task 5: Tune your classifier to achieve better than .3 precision and recall

### using our testing script. Check the tester.py script in the final project

### folder for details on the evaluation method, especially the test_classifier

### function. Because of the small size of the dataset, the script uses

### stratified shuffle split cross validation. For more info:

### http://scikit-learn.org/stable/modules/generated/sklearn.cross_validation.StratifiedShuffleSplit.html

def TuneKNN(features, labels,features_list,folds = 100):

return PipeOpt

def TuneSVM(features, labels,features_list,folds = 100):

return PipeOpt

#How do I use class_weight?

def TuneDT(features, labels,features_list,folds = 100):

return PipeOpt

def NoTuneDT(features, labels,features_list,folds = 100):

return PipeOpt

'''

### Task 6: Dump your classifier, dataset, and features_list so anyone can

### check your results. You do not need to change anything below, but make sure

### that the version of poi_id.py that you submit can be run on its own and

### generates the necessary .pkl files for validating your results.

'''

'''

#Potential Features

'salary', 'to_messages', 'deferral_payments', 'total_payments', 'exercised_stock_options',

'bonus', 'restricted_stock', 'shared_receipt_with_poi', 'restricted_stock_deferred',

'total_stock_value', 'expenses', 'loan_advances', 'from_messages', 'other',

'from_this_person_to_poi', 'poi', 'director_fees', 'deferred_income',

'long_term_incentive', 'email_address', 'from_poi_to_this_person',

##Added

fraction_from_poi,fraction_to_poi

'''

#Why was AdaBoost So Much less effective than normal DT

#Regarding Training Set

#https://discussions.udacity.com/t/p5-testing-results-all-over-the-place/37850/9

def main():

test_classifier(clf, my_dataset, features_list)

main()