jsun

#!/bin/bash
#$ -l rt_F=10
#$ -l h_rt=24:00:00
#$ -j y
#$ -cwd
#$ -N qn_makeGenomeIndex

pDwGenome=0         # download sequences and annotations from IWGSC server
pSplitGenomeSeq=0   # split whole genome sequences into A, B, and D subgenomes
pLAST=0             # use LAST to find homologoues sequences

jsun

from sklearn.datasets import fetch_mldata
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import KernelPCA
import matplotlib.pyplot as plt

# download MNIST data
mnist = fetch_mldata('MNIST original', data_home='./data/minist')

print(mnist)

jsun

import numpy as np
from sklearn import datasets
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.grid_search import GridSearchCV
from sklearn.model_selection import cross_val_score

jsun

import numpy as np
from sklearn import datasets
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.svm import SVC
from sklearn.grid_search import GridSearchCV

# load data

jsun

from sklearn import datasets
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.svm import SVC
from sklearn.learning_curve import validation_curve
import matplotlib.pyplot as plt
import numpy as np

jsun

from sklearn import datasets
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.ensemble import RandomForestClassifier
from sklearn.learning_curve import learning_curve
import matplotlib.pyplot as plt
import numpy as np

jsun

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix

cancer = datasets.load_breast_cancer()
x = cancer.data
y = cancer.target

jsun

from sklearn import datasets
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix

cancer = datasets.load_breast_cancer()
x = cancer.data

jsun

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix

cancer = datasets.load_breast_cancer()
x = cancer.data
y = cancer.target

jsun

from sklearn.datasets import fetch_mldata
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix

# get training and test sets
x_train, x_test, y_train, y_test = train_test_split(mnist.data, mnist.target, test_size=0.2, random_state=0)
print(x_train.shape)