지방이의 Data Science Lab

test2_act['week'] = np.floor((test2_act['day'] -1)/ 7 +1 ) temp['dayofweek'] = temp['day'] % 7 + 1

def resumetable(df): print(f"Dataset Shape: {df.shape}") summary = pd.DataFrame(df.dtypes,columns=['dtypes']) summary = summary.reset_index() summary['Name'] = summary['index'] summary = summary[['Name','dtypes']] summary['Min'] = df.min().values summary['Max'] = df.max().values summary['Missing'] = df.isnull().sum().values summary['Uniques'] = df.nunique().values return summary train_label = pd..

temp = pd.merge(final, train_activity.groupby('acc_id')['npc_kill'].sum().to_frame('is_npc_kill').reset_index(), on ='acc_id', how='left') temp['is_npc_kill'] = np.where(temp['is_npc_kill']==0, 1, 0)

sum(temp,[]) list(set(tempp)

import matplotlib.pyplot as plt import matplotlib.image as mpimg image = mpimg.imread("map.png") plt.figure(figsize = (100,50)) plt.imshow(image) #plt.show()

1 2 3 4 5 6 7 from sklearn.model_selection import train_test_split from sklearn.model_selection import GroupShuffleSplit train_inds, test_inds=next(GroupShuffleSplit(test_size=.2,n_splits=2,random_state=7).split(data,groups=data['acc_id'])) train=data.iloc[train_inds] test=data.iloc[test_inds] Colored by Color Scripter

1 2 3 df = df.astype({'a':np.int32, 'b':np.float32}) df['acc_id'].astype('int64',inplace = True) manu_y['신용등급'] = pd.to_numeric(manu_y['신용등급'])

hrs = trade.time.astype(str).apply(lambda x: x.split(':')[0]).astype(float) hrs = hrs.to_frame('hrs') trade= pd.concat([trade,hrs],axis=1) def get_part_of_day(hour): return ( "morning" if 5