def benchmark_solution():
train=load_data('train.csv')
test=load_data('test.csv')
lbl_enc = preprocessing.LabelEncoder()
train['target'] = lbl_enc.fit_transform(train['target'])
feature_cols= [col for col in train.columns if col not in ['target','id']]
X_train=train[feature_cols]
y=train['target']
X_test=test[feature_cols]
test_ids=test['id']
print "benchmark solution"
cross_v(get_rf(),X_train.values,y.values)#0.596256539386
def feature_engineering_solution():
train=load_data('train.csv')
test=load_data('test.csv')
le = preprocessing.LabelEncoder()
le.fit(train['target'])
train['target']=le.transform(train['target'])
feature_cols= [col for col in train.columns if col not in ['target','id']]
X_train=feature_engineering(train[feature_cols])
X_test=feature_engineering(test[feature_cols])
feature_cols= [col for col in X_train.columns]#std 0.607958003167 mean 0.615741311533
X_train=X_train[feature_cols]
X_test=X_test[feature_cols]
y=train['target']
test_ids=test['id']
print 'feature_engineering_solution'
cross_v(get_rf(),X_train.values,y.values)#0.600017926514
def parameter_tuning_solution():
train=load_data('train.csv')
test=load_data('test.csv')
le = preprocessing.LabelEncoder()
le.fit(train['target'])
train['target']=le.transform(train['target'])
feature_cols= [col for col in train.columns if col not in ['target','id']]
X_train=train[feature_cols]
X_test=test[feature_cols]
y=train['target']
test_ids=test['id']
print 'parameter_tuning_solution800_6'
cross_v(get_tuned_rf(),X_train.values,y.values)#0.546637992781
clf=get_tuned_rf()
clf.fit(X_train,y)
preds = clf.predict_proba(X_test)
write_submission(test_ids,preds,'submissions/parameter_tuning_solution800_6.csv')
def clf_score(models,X_train,y_train):
index=[]
score=[]
for clf in models:
index.append(clf[0])
cv=cross_v(clf[1],X_train.values,y_train.values)
print clf[0]
print cv
score.append(cv)
return pd.DataFrame(score,index=index)
def feature_selection_solution():
train=load_data('train.csv')
test=load_data('test.csv')
le = preprocessing.LabelEncoder()
le.fit(train['target'])
train['target']=le.transform(train['target'])
feature_cols= [col for col in train.columns if col not in ['target','id']]
X_train=feature_engineering(train[feature_cols])
X_test=feature_engineering(test[feature_cols])
feature_cols=[col for col in X_train.columns if col not in ['mean','std','nonzero','feat_6','feat_82','feat_84']]
X_train=X_train[feature_cols]
X_test=X_test[feature_cols]
print X_train.columns
y=train['target']
test_ids=test['id']
print 'feature_selection_solution'
cross_v(get_rf(),X_train.values,y.values)# mean 0.595288515439 std 0.593551044059 nonzero 0.597406303207
#no fg 6 82 84 0.603600594376
#0.600058535601
clf=get_rf()
clf.fit(X_train,y)
preds = clf.predict_proba(X_test)
write_submission(test_ids,preds,'submissions/feature_selection_rf100_84_82_6_nofg.csv')
clf=clfs[name]['est'](**params)
print name
#cross_v(clf,X_train.values,y.values)
clf.fit(X_train.values,y.values)
def main():
train=load_data('train.csv')
feature_cols= [col for col in train.columns if col not in ['target','id']]
X_train=feature_engineering(train[feature_cols])
y=train['target']
grid_search(X_train,y,get_clfs())
#if __name__ == '__main__':
# main()
train=load_data('train.csv')
le = preprocessing.LabelEncoder()
le.fit(train['target'])
train['target']=le.transform(train['target'])
feature_cols= [col for col in train.columns if col not in ['target','id']]
X_train=train[feature_cols]
y=train['target']
clfs=get_gb()
for name, clf in clfs.iteritems():
print name
param_list = list(ParameterGrid(clfs[name]['grid']))
for i in range(0,len(param_list)):
clf=clfs[name]['est'].set_params(**param_list[i])
print clf
print param_list[i]
cross_v(clf,X_train.values,y.values)