这里列出了使用基于bin的求和的 两个 基于NumPy的 两个 三三个 解决方案，基本上涵盖了三种情况。
方案1：每个日期有多个条目，但没有缺失的日期
方法1：
# For now hard-pred to use Window size of 5 and stride length of 3def vectorized_app1(df): # Extract the index names and values vals = df.A.values indx = df.index.values # Extract IDs for bin based summing mask = np.append(False,indx[1:] > indx[:-1]) date_id = mask.cumsum() search_id = np.hstack((0,np.arange(2,date_id[-1],3),date_id[-1]+1)) shifts = np.searchsorted(date_id,search_id) reps = shifts[1:] - shifts[:-1] id_arr = np.repeat(np.arange(len(reps)),reps) # Perform bin based summing and subtract the repeated ones IDsums = np.bincount(id_arr,vals) allsums = IDsums[:-1] + IDsums[1:] allsums[1:] -= np.bincount(date_id,vals)[search_id[1:-2]] # Convert to pandas dataframe if needed out_index = indx[np.nonzero(mask)[0][3::3]] # Use last date of group return pd.Dataframe(allsums,index=out_index,columns=['A'])
方法2：
# For now hard-pred to use Window size of 5 and stride length of 3def vectorized_app2(df): # Extract the index names and values indx = df.index.values # Extract IDs for bin based summing mask = np.append(False,indx[1:] > indx[:-1]) date_id = mask.cumsum() # Generate IDs at which shifts are to happen for a (2,3,5,8..) patttern # Pad with 0 and length of array at either ends as we use diff later on shiftIDs = (np.arange(2,date_id[-1],3)[:,None] + np.arange(2)).ravel() search_id = np.hstack((0,shiftIDs,date_id[-1]+1)) # Find the start of those shifting indices # Generate ID based on shifts and do bin based summing of dataframe shifts = np.searchsorted(date_id,search_id) reps = shifts[1:] - shifts[:-1] id_arr = np.repeat(np.arange(len(reps)),reps) IDsums = np.bincount(id_arr,df.A.values) # Sum each group of 3 elems with a stride of 2, make dataframe if needed allsums = IDsums[:-1:2] + IDsums[1::2] + IDsums[2::2] # Convert to pandas dataframe if needed out_index = indx[np.nonzero(mask)[0][3::3]] # Use last date of group return pd.Dataframe(allsums,index=out_index,columns=['A'])
方法3：
def vectorized_app3(df, S=3, W=5): dt = df.index.values shifts = np.append(False,dt[1:] > dt[:-1]) c = np.bincount(shifts.cumsum(),df.A.values) out = np.convolve(c,np.ones(W,dtype=int),'valid')[::S] out_index = dt[np.nonzero(shifts)[0][W-2::S]] return pd.Dataframe(out,index=out_index,columns=['A'])
我们可以将卷积部分替换为直接切片求和，以获取其修改版本-
def vectorized_app3_v2(df, S=3, W=5): dt = df.index.values shifts = np.append(False,dt[1:] > dt[:-1]) c = np.bincount(shifts.cumsum(),df.A.values) f = c.size+S-W out = c[:f:S].copy() for i in range(1,W): out += c[i:f+i:S] out_index = dt[np.nonzero(shifts)[0][W-2::S]] return pd.Dataframe(out,index=out_index,columns=['A'])
方案2：每个日期和缺少的日期有多个条目
方法4：
def vectorized_app4(df, S=3, W=5): dt = df.index.values indx = np.append(0,((dt[1:] - dt[:-1])//86400000000000).astype(int)).cumsum() WL = ((indx[-1]+1)//S) c = np.bincount(indx,df.A.values,minlength=S*WL+(W-S)) out = np.convolve(c,np.ones(W,dtype=int),'valid')[::S] grp0_lastdate = dt[0] + np.timedelta64(W-1,'D') freq_str = str(S)+'D' grp_last_dt = pd.date_range(grp0_lastdate, periods=WL, freq=freq_str).values out_index = dt[dt.searchsorted(grp_last_dt,'right')-1] return pd.Dataframe(out,index=out_index,columns=['A'])
方案3：连续的日期，每个日期只有一个条目
方法5：
def vectorized_app5(df, S=3, W=5): vals = df.A.values N = (df.shape[0]-W+2*S-1)//S n = vals.strides[0] out = np.lib.stride_tricks.as_strided(vals,shape=(N,W), strides=(S*n,n)).sum(1) index_idx = (W-1)+S*np.arange(N) out_index = df.index[index_idx] return pd.Dataframe(out,index=out_index,columns=['A'])
创建测试数据的建议
场景1：
# Setup input for multiple dates, but no missing datesS = 4 # Stride length (Could be edited)W = 7 # Window length (Could be edited)datasize = 3 # Decides datasizetidx = pd.date_range('2012-12-31', periods=datasize*S + W-S, freq='D')start_df = pd.Dataframe(dict(A=np.arange(len(tidx))), tidx)reps = np.random.randint(1,4,(len(start_df)))idx0 = np.repeat(start_df.index,reps)df_data = np.random.randint(0,9,(len(idx0)))df = pd.Dataframe(df_data,index=idx0,columns=['A'])场景2：
要为多个日期和缺少日期的日期创建设置，我们可以只编辑
df_data创建步骤，如下所示-
df_data = np.random.randint(0,9,(len(idx0)))
方案3：
# Setup input for exactly one entry per dateS = 4 # Could be editedW = 7datasize = 3 # Decides datasizetidx = pd.date_range('2012-12-31', periods=datasize*S + W-S, freq='D')df = pd.Dataframe(dict(A=np.arange(len(tidx))), tidx)
