KestindotC

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten, Reshape
from keras.layers.convolutional import Convolution1D, Convolution2D, MaxPooling2D
from keras.utils import np_utils


def myGenerator():
    (X_train, y_train), (X_test, y_test) = mnist.load_data()
    y_train = np_utils.to_categorical(y_train,10)

KestindotC

import argparse
import os

import pandas as pd
import pyspark.sql.functions as F
from pyspark.sql import SparkSession
from pyspark.sql.types import StringType, IntegerType, ArrayType

from build_graph import *
from avg_response_time import *

KestindotC

import pandas as pd
from sklearn.ensemble import IsolationForest
ilf = IsolationForest(n_estimators=100,
                      contamination=0.02,
                      verbose=2)

# DataSet download from https://github.com/shngli/Machine-learning/blob/master/Anomaly%20Detection/ex8data1.mat
# Using scipy and numpy to transform .mat -> .csv

df = pd.read_csv('dataset.csv',header=None)

KestindotC

import pymysql
import pandas as pd
from sqlalchemy import create_engine

engine = create_engine('mysql+pymysql://kestin_chang:<password>@<RDS-endpointURL>:3306/<DBname>')

# Pandas read_sql function
df = pd.read_sql_query('SELECT * FROM <TABLE NAME> LIMIT 10',engine)

# Print result

KestindotC

# List unique values in a DataFrame column
pd.unique(df.column_name.ravel())

# Convert Series datatype to numeric, getting rid of any non-numeric values
df['col'] = df['col'].astype(str).convert_objects(convert_numeric=True)

# Grab DataFrame rows where column has certain values
valuelist = ['value1', 'value2', 'value3']
df = df[df.column.isin(valuelist)]

KestindotC

KestindotC

KestindotC

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */
import java.util.*;
/**
 *
 * @author Kestin
 */

KestindotC

/*
* To change this license header, choose License Headers in Project Properties.
* To change this template file, choose Tools | Templates
* and open the template in the editor.
*/
import java.util.*;
/**
 * Implementation of ArrayList using array data structure
 * Other implementation (e.g. LinkList) were record in other files
 * @author Kestin

KestindotC

TCGA Data Download Tutorial

TCGA GDC Client 的程式使用的是Python2.7以及提供Ubuntu 12.0以上的安裝套件
實驗室的工作站 Distro 是 Centos6.4
如果大家對鳥哥還有點印象的話應該可以知道是Redhat/CentOS/Fedora系列的Distributions
所以請使用Miniconda建立該下載工具需要的環境並且使用source code來安裝工具

---

conda config --add channels r