def main():
print("PCA")
pca.pca()
print("RandomForest")
rf.rf(2)
print("KNN")
knn.knn(2)
print("SVC")
svc.svc()
print("GRID_SVC")
svc.gridSearchScore()
print("Logistic")
logistic.Logistic().fit()
print("DNN Classifier")
classifier_model = classifier.classifier()
classifier_model.fit()
""" random forest for forest types dataset """
import pandas as pd
import numpy as np
from sklearn import cross_validation
from rf import rf # custom function (in rf.py) for random forests
import os
os.chdir("/Users/sandy/work/UF/ML/Project/code/RandomForests")
""" training.csv """
train = pd.read_csv("../../datasets/ForestTypes/training.csv")
features = train.columns[1:]
X_train = train[features]
X_train = X_train.astype(float)
y_train = train['class']
""" testing.csv """
test = pd.read_csv("../../datasets/ForestTypes/testing.csv")
features = test.columns[1:]
X_test = test[features]
X_test = X_test.astype(float)
y_test = test['class']
print rf(X_train, X_test, y_train, y_test, "Forest types")
import os
os.chdir("/Users/sandy/work/UF/ML/Project/code/RandomForests")
""" breast-cancer-wisconsin.data """
data = pd.read_csv(
"../../datasets/breast-cancer-wisconsin/breast-cancer-wisconsin.data",
header=None)
data = data.replace('?', np.nan).astype(float, raise_on_error=False).dropna(
how='any') # removing missing values
num_columns = len(data.columns)
features = data.columns[1:-1]
X = data[features]
y = data[num_columns - 1]
X_train, X_test, y_train, y_test = cross_validation.train_test_split(
X, y, test_size=0.1, random_state=0)
print rf(X_train, X_test, y_train, y_test, "Wisconsin Breast Cancer Database")
""" wdbc.data """
data = pd.read_csv("../../datasets/breast-cancer-wisconsin/wdbc.data",
header=None)
data = data.astype(float, raise_on_error=False).dropna(
how='any') # removing missing values
features = data.columns[2:]
X = data[features]
y = data[1]
X_train, X_test, y_train, y_test = cross_validation.train_test_split(
X, y, test_size=0.1, random_state=0)
print rf(X_train, X_test, y_train, y_test,
"Wisconsin Diagnostic Breast Cancer")
""" wpbc.data """
data = pd.read_csv("../../datasets/breast-cancer-wisconsin/wpbc.data",
header=None)
""" random forest for forest types dataset """
import pandas as pd
import numpy as np
from sklearn import cross_validation
from rf import rf # custom function (in rf.py) for random forests
import os
os.chdir("/Users/sandy/work/UF/ML/Project/code/RandomForests")
""" training.csv """
train = pd.read_csv("../../datasets/ForestTypes/training.csv")
features = train.columns[1:]
X_train = train[features]
X_train = X_train.astype(float)
y_train = train['class']
""" testing.csv """
test = pd.read_csv("../../datasets/ForestTypes/testing.csv")
features = test.columns[1:]
X_test = test[features]
X_test = X_test.astype(float)
y_test = test['class']
print rf(X_train, X_test, y_train, y_test,"Forest types")
from metric import printErrorMetrics
from rf import rf
from rr import rr
from nn import nn
from lr import lr
if __name__ == '__main__':
extract_dir = sys.argv[1]
fnum = int(sys.argv[2])
""" datasets and labels's size is fnum """
datasets, labels = GetAllData(extract_dir, fnum, 'bfs', total_vertex_num=4900578, L=500000)
# datasets, labels = GetAllData(extract_dir, fnum, 'bfs', total_vertex_num=65608366, L=10000000)
""" ridge regression """
sr, sl = rr(datasets, labels, fnum)
""" neural network """
sr, sl = nn(datasets, labels, fnum)
""" liner regression """
sr, sl = lr(datasets, labels, fnum)
""" random forest """
sr, sl = rf(datasets, labels, fnum)
""" draw picture """
sample_draw(sr,sl)
import rf
# First get data by running this command in the console
# obspyDMT --identity 'TA.Z30A.*.BHZ' --min_mag '5.8' --min_date '2011-01-01' --max_date '2011-01-10' --event_catalog 'IRIS' --arc 'N'
# Set data path of obspyDMT here or in conf.py
rf.set_paths('~/obspyDMT-data/2011-01-01_2011-01-10_5.8_9.9')
# Convert pickled events to catalog file events.xml
rf.convert_dmteventfile()
# Select events for RF
rf.create_rfeventsfile(filters=[])
# Calculate RFs. They will be in the RF directory of the corresponding event
rf.rf('dmt', downsample=10)
if int(rec0) == 1:
uid = input('which user you want to apply(0~3065)\n-->')
uid = int(input('which user you want to apply(0~3065)\n-->'))
n = int(input('how many item you want to recommandat, as int\n-->'))
if int(algo) == 3:
fac = int(input('how many factors you want, as int\n-->'))
result = svdrec(factors=fac)
caculate_mse(result)
if int(cm) == 1:
drawcm(result, title='MF')
if int(rec0) == 1:
uid = int(input('which user you want to apply(0~3065)\n-->'))
n = int(input('how many item you want to recommandat, as int\n-->'))
rec(result, uid, n, rawId=True)
if int(algo) == 4:
result = cf()
caculate_mse(result)
if int(cm) == 1:
drawcm(result, title='MF')
if int(rec0) == 1:
uid = int(input('which user you want to apply(0~3065)\n-->'))
n = int(input('how many item you want to recommandat, as int\n-->'))
rec(result, uid, n, rawId=True)
if int(algo) == 5:
a = rf()
""" random forest for handwritten digits dataset """
import pandas as pd
import numpy as np
from sklearn import cross_validation
from rf import rf # custom function (in rf.py) for random forests
import os
os.chdir("/Users/sandy/work/UF/ML/Project/code/RandomForests")
""" optdigits.tra """
train = pd.read_csv("../../datasets/optdigits/optdigits.tra", header=None)
num_columns = len(train.columns)
features = train.columns[:-1]
X_train = train[features]
y_train = train[num_columns - 1]
""" optdigits.tes """
test = pd.read_csv("../../datasets/optdigits/optdigits.tes", header=None)
num_columns = len(train.columns)
features = test.columns[:-1]
X_test = test[features]
y_test = test[num_columns - 1]
print rf(X_train, X_test, y_train, y_test,
"Optical Recognition of Handwritten Digits")
for c in cuenta1:
valor1 = c.cuenta
for c in cuenta2:
valor2 = c.cuenta
if valor1 < valor2:
mini = valor1
else:
mini = valor2
if mini> nnodes:
mini = nnodes/2
nodes1 = neo4j.CypherQuery(graph_db, "match (n:"+tipo+") where n."+target+" <> '"+vtarget+ "' return n,id(n) as id,n."+target+" as "+target+" LIMIT "+str(mini)+" UNION ALL "+"match (n:"+tipo+") where n."+target+" = '"+vtarget+ "' return n,id(n) as id,n."+target+" as "+target+" LIMIT "+str(mini)).execute()
print "Conjunto de nodos cargado: "+str(len(nodes1.data))+" elementos."
nodestrain = []
nodestest = []
for z in nodes1:
if random.randint(0,5)>1:
nodestrain.append(z)
else:
nodestest.append(z)
print "Conjunto de entrenamiento: "+str(len(nodestrain))+" elementos."
print "Conjunto de prueba: "+str(len(nodestest))+" elementos."
#graph, tipo, target, vtarget, narboles, nnodos, nrels, maxdepth, exrels,umbral
rf = rf(graph_db,nodestrain,tipo,target,vtarget,1,nnodes,100,2,[],0 )
rf.train()
rf.test(nodestest)
np.save("rf2", rf)
a_g,
trace,
dict_of_all_sp_grt,
initial_sp_c,
grt_dict,
stoichiometric_dict,
switch,
temperature,
v=v,
pressure=pressure)
# =========================================================================
# Release fraction module
# =========================================================================
species_updated = sp_g + sp_c
rf.rf(y, species_updated, input1, stoichiometric_dict, el_inventory)
elif method == 'SLSQP':
a = np.zeros([len(input1), len(species)])
x0 = np.ones(len(species)) * 0.1
k1 = 0
for j in species:
a[:, k1] = stoichiometric_coeff_matrix_generator.stoi(
j, input1, stoichiometric_dict)
k1 = k1 + 1
no_it = 20
opt1 = {
'eps': 1e-3,
'maxiter': 20000,
'ftol': 1e-6,
from sklearn import cross_validation
from rf import rf # custom function (in rf.py) for random forests
import os
os.chdir("/Users/sandy/work/UF/ML/Project/code/RandomForests")
""" breast-cancer-wisconsin.data """
data = pd.read_csv("../../datasets/breast-cancer-wisconsin/breast-cancer-wisconsin.data",header=None)
data = data.replace('?',np.nan).astype(float,raise_on_error=False).dropna(how='any') # removing missing values
num_columns = len(data.columns)
features = data.columns[1:-1]
X = data[features]
y = data[num_columns-1]
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X,y,test_size=0.1,random_state=0)
print rf(X_train, X_test, y_train, y_test,"Wisconsin Breast Cancer Database")
""" wdbc.data """
data = pd.read_csv("../../datasets/breast-cancer-wisconsin/wdbc.data",header=None)
data = data.astype(float,raise_on_error=False).dropna(how='any') # removing missing values
features = data.columns[2:]
X = data[features]
y = data[1]
X_train, X_test, y_train, y_test = cross_validation.train_test_split(X,y,test_size=0.1,random_state=0)
print rf(X_train, X_test, y_train, y_test,"Wisconsin Diagnostic Breast Cancer")
""" wpbc.data """
data = pd.read_csv("../../datasets/breast-cancer-wisconsin/wpbc.data",header=None)
data = data.replace('?',np.nan).astype(float,raise_on_error=False).dropna(how='any') # removing missing values
features = data.columns[3:]
X = data[features]
""" random forest for handwritten digits dataset """
import pandas as pd
import numpy as np
from sklearn import cross_validation
from rf import rf # custom function (in rf.py) for random forests
import os
os.chdir("/Users/sandy/work/UF/ML/Project/code/RandomForests")
""" optdigits.tra """
train = pd.read_csv("../../datasets/optdigits/optdigits.tra",header=None)
num_columns = len(train.columns)
features = train.columns[:-1]
X_train = train[features]
y_train = train[num_columns-1]
""" optdigits.tes """
test = pd.read_csv("../../datasets/optdigits/optdigits.tes",header=None)
num_columns = len(train.columns)
features = test.columns[:-1]
X_test = test[features]
y_test = test[num_columns-1]
print rf(X_train, X_test, y_train, y_test,"Optical Recognition of Handwritten Digits")
print(x) print(y) print(z) x, y, z = svm() print(x) print(y) print(z) x, y, z = nb() print(x) print(y) print(z) x, y, z = dt() print(x) print(y) print(z) x, y, z = rf() print(x) print(y) print(z) x, y, z = gbm() print(x) print(y) print(z) x, y, z = knn() print(x) print(y) print(z) x, y, z = ada() print(x) print(y) print(z)
import obspy.iris
import rf
# Create getwaveform function which has to be passed to rf function
client = obspy.iris.Client()
def getwaveform(station, t1, t2):
return client.getWaveform('TA', station, '', 'BH?', t1, t2)
# Set output path here or in config file
rf.set_paths('~/obspyDMT-data/client_test')
# Create event file from given events
rf.create_rfeventsfile('./events.xml')
#Calculate receiver functions. Station coordinates are given in stations.txt
rf.rf('client', getwaveform, './stations.txt', deconvolve='freq')
