return data.iloc[1:]
ans = augment(a,
ignore_index=1,
times=1,
std=0.1,
sample_size=1000,
add_initial=False)
#%%
#dataset = gf.get_dataset()
dataset = X_train.copy()
length = len(dataset)
new = pd.DataFrame()
for i in range(length):
row = dataset.iloc[[i]]
row.insert(0, 'y', y_train.iloc[i])
ans = augment(row,
ignore_index=0,
times=1,
std=0.1,
sample_size=1000,
add_initial=False)
new = new.append(ans)
#%%
dataset = dataset.append(new)
[X_train, X_test, y_train, y_test] = gf.divide(dataset)
print(gf.run_xgboost(X_train, y_train, X_test, y_test))
#a,b=augmenter(X_train,y_train,sd=0.1,col=1)
def get_index_combo(data, num):
lis = gf.get_top_n(data["accuracy"], num)
temp = gf.subsets(lis)
return temp
index_list = get_index_combo(data, 7)
data1 = pd.DataFrame()
for i in index_list:
Xt, yt = X_train.copy(), y_train.copy()
print("Currently augmenting")
print(i)
for j in i:
Xtr, ytr = augmenter(X_train.copy(), y_train.copy(), sd=0.1,
col=j) #creating augmented values
Xt = Xt.append(Xtr)
yt = yt.append(pd.Series(ytr))
d = gf.run_xgboost(Xt, yt, X_test, y_test)
d["combination"] = i
data1 = data1.append(d, ignore_index=True)
print(d["accuracy"])
print("-------")
data1.to_csv("data/data3.csv")
Xtr = gf.loadfile("Xtr")
Xte = gf.loadfile("Xte")
ytr = gf.loadfile("ytr")
yte = gf.loadfile("yte")
temp = gf.convertstrtolist(temp)
Xt,yt = Xtr.copy(),ytr.copy()
print("Currently augmenting")
for j in temp:
Xtr1,ytr1=augmenter(Xtr.copy(),ytr.copy(),sd=0.1,col=j) #creating augmented values
Xt = Xt.append(Xtr1)
yt = yt.append(pd.Series(ytr1))
print("Augmenting Finished")
d = gf.run_xgboost(Xt,yt,Xte,yte)
print(d)
"""
{'accuracy': 0.882377508399508, 'std': 0.012872278905955601, 'AUC': 0.7476636185875316}
"""
#%%
data = pd.DataFrame()
for i in range(150):
print(i)
Xt1,yt1= augmenter(Xt.copy(),yt.copy(),0.2,i)
d = gf.run_xgboost(Xt1,yt1,Xte,yte)
data= data.append(d,ignore_index=True)
@author: adityavyas
"""
import global_functions as gf
import pandas as pd
[X_train, X_test, y_train, y_test] = gf.get_dataset()
def run150(df):
for index in range(150):
df = gf.add_gaussian_index(df, index)
return df
data = pd.DataFrame()
runnable = X_train.copy()
runnabletrain = y_train.copy()
for i in range(1, 10):
df = X_train.copy()
for j in range(i):
df = run150(df)
runnable = pd.concat([runnable, df])
runnabletrain = pd.concat([runnabletrain, y_train.copy()])
frame = gf.run_xgboost(runnable, runnabletrain, X_test, y_test)
data = data.append(frame, ignore_index=True)
print(frame)