Matthew Mayo mmmayo13

## pipelines-2a.py
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.pipeline import Pipeline
from sklearn import tree

# Load and split the data
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=42)

## pipelines-1.py
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.pipeline import Pipeline
from sklearn.externals import joblib
from sklearn.linear_model import LogisticRegression
from sklearn import svm
from sklearn import tree

## check_wiki_corpus.py
"""
Checks a corpus created from a Wikipedia dump file.
"""

import sys, time

def check_corpus(input_file):

    """Reads some lines of corpus from text file"""

## make_wiki_corpus.py
"""
Creates a corpus from Wikipedia dump file.

Inspired by:
https://github.com/panyang/Wikipedia_Word2vec/blob/master/v1/process_wiki.py
"""

import sys
from gensim.corpora import WikiCorpus

## penalty.csv

          
            Practice
            Outcome

            
              0
              0

            
              0.3
              0

            
              1
              0

            
              1.2
              0

            
              2
              0

            
              2.2
              0

            
              2.6
              0

            
              3
              0

            
              3.1
              0

## cola.csv

          
            Temperature
            Cola

            
              1
              1

            
              2
              1

            
              3
              1

            
              4
              1

            
              5
              1

            
              6
              1

            
              7
              1

            
              8
              1

            
              9
              2

## keras-ex-maggio.py
from keras.models import Sequential
from keras.layers import Dense, Activation

dims = X_train.shape[1]
print(dims, 'dims')
print("Building model...")

nb_classes = Y_train.shape[1]
print(nb_classes, 'classes')

## glm-r-example.r
## Simple Linear Regression using R

#Install Package
install.packages("hydroGOF")
library("hydroGOF")

#Read data from .csv file
data = read.csv("Cola.csv", header = T)
head(data)

## data-imputation.r
#Loading the mice package
library(mice)
#Loading the following package for looking at the missing values
library(VIM)
library(lattice)
data(nhanes)

# First look at the data
str(nhanes)

## tic-tac-toe-keras.py
import numpy as np
import pandas as pd

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix

from keras.models import Sequential
from keras.layers import Dense
	from sklearn.datasets import load_iris
	from sklearn.model_selection import train_test_split
	from sklearn.preprocessing import StandardScaler
	from sklearn.decomposition import PCA
	from sklearn.pipeline import Pipeline
	from sklearn import tree

	# Load and split the data
	iris = load_iris()
	X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=42)
	"""
	Checks a corpus created from a Wikipedia dump file.
	"""

	import sys, time

	def check_corpus(input_file):

	"""Reads some lines of corpus from text file"""
	"""
	Creates a corpus from Wikipedia dump file.

	Inspired by:
	https://github.com/panyang/Wikipedia_Word2vec/blob/master/v1/process_wiki.py
	"""

	import sys
	from gensim.corpora import WikiCorpus
	from keras.models import Sequential
	from keras.layers import Dense, Activation

	dims = X_train.shape[1]
	print(dims, 'dims')
	print("Building model...")

	nb_classes = Y_train.shape[1]
	print(nb_classes, 'classes')
	## Simple Linear Regression using R

	#Install Package
	install.packages("hydroGOF")
	library("hydroGOF")

	#Read data from .csv file
	data = read.csv("Cola.csv", header = T)
	head(data)
	#Loading the mice package
	library(mice)
	#Loading the following package for looking at the missing values
	library(VIM)
	library(lattice)
	data(nhanes)

	# First look at the data
	str(nhanes)
	import numpy as np
	import pandas as pd

	from sklearn.preprocessing import LabelEncoder, OneHotEncoder
	from sklearn.model_selection import train_test_split
	from sklearn.metrics import confusion_matrix

	from keras.models import Sequential
	from keras.layers import Dense