基于所有组合的索引和分组创建内部python循环
我有一个脚本，它查看属于一个组（REG_ID）的行和列标题，并对值求和。代码在矩阵（小子集）上运行，如下所示：基于所有组合的索引和分组创建内部python循环,python,dataframe,enumerate,Python,Dataframe,Enumerate,我有一个脚本，它查看属于一个组（REG_ID）的行和列标题，并对值求和。代码在矩阵（小子集）上运行，如下所示： global index index = 1 x = index while index < len(idgroups): ward_list = idgroups[index] #select list of ward ids for each region from list of lists df6 = mergedcsv.loc[ward_list] #s
global index
index = 1
x = index
while index < len(idgroups):
ward_list = idgroups[index] #select list of ward ids for each region from list of lists
df6 = mergedcsv.loc[ward_list] #select rows with values in the list
dfcols = mergedcsv.loc[ward_list, :] #select columns with values in list
ward_liststr = map(str, ward_list) #convert ward_list to strings so that they can be used to select columns, won't work as integers.
ward_listint = map(int, ward_list)
#dfrowscols = mergedcsv.loc[ward_list, ward_listint]
df7 = df6.loc[:, ward_liststr]
print df7
regflowsum = df7.values.sum() #sum all values in dataframe
intflow = [regflowsum]
print intflow
dfintflow = pd.DataFrame(intflow)
dfintflow.reset_index(level=0, inplace=True)
dfintflow.columns = ["RegID", "regflowsum"]
dfflows.set_value(index, 'RegID', index)
dfflows.set_value(index, 'RegID2', index)
dfflows.set_value(index, 'regflow', regflowsum)
mergedcsv.set_value(ward_list, 'TotRegFlows', regflowsum)
index += 1 #increment index number
print dfflows
new_df = pd.merge(pairlist, dfflows, how='left', left_on=['origID','destID'], right_on = ['RegID', 'RegID2'])
print new_df #useful for checking dataframe merges
regionflows = r"C:\Temp\AllNI\regionflows.csv"
header = ["WardID","LABEL","REG_ID","Total","TotRegFlows"]
mergedcsv.to_csv(regionflows, columns = header, index=False)
regregflows = r"C:\Temp\AllNI\reg_regflows.csv"
headerreg = ["REG_ID_ORIG", "REG_ID_DEST", "FLOW"]
pairlistCSV = r"C:\Temp\AllNI\pairlist_regions.csv"
new_df.to_csv(pairlistCSV)
global index
index = 1
x = index
while index < len(idgroups):
ward_list = idgroups[index] #select list of ward ids for each region from list of lists
df6 = mergedcsv.loc[ward_list] #select rows with values in the list
dfcols = mergedcsv.loc[ward_list, :] #select columns with values in list
ward_liststr = map(str, ward_list) #convert ward_list to strings so that they can be used to select columns, won't work as integers.
ward_listint = map(int, ward_list)
#dfrowscols = mergedcsv.loc[ward_list, ward_listint]
df7 = df6.loc[:, ward_liststr]
print df7
regflowsum = df7.values.sum() #sum all values in dataframe
intflow = [regflowsum]
print intflow
dfintflow = pd.DataFrame(intflow)
dfintflow.reset_index(level=0, inplace=True)
dfintflow.columns = ["RegID", "regflowsum"]
dfflows.set_value(index, 'RegID', index)
dfflows.set_value(index, 'RegID2', index)
dfflows.set_value(index, 'regflow', regflowsum)
mergedcsv.set_value(ward_list, 'TotRegFlows', regflowsum)
index += 1 #increment index number
print dfflows
new_df = pd.merge(pairlist, dfflows, how='left', left_on=['origID','destID'], right_on = ['RegID', 'RegID2'])
print new_df #useful for checking dataframe merges
regionflows = r"C:\Temp\AllNI\regionflows.csv"
header = ["WardID","LABEL","REG_ID","Total","TotRegFlows"]
mergedcsv.to_csv(regionflows, columns = header, index=False)
regregflows = r"C:\Temp\AllNI\reg_regflows.csv"
headerreg = ["REG_ID_ORIG", "REG_ID_DEST", "FLOW"]
pairlistCSV = r"C:\Temp\AllNI\pairlist_regions.csv"
new_df.to_csv(pairlistCSV)
我已经尝试了很多关于数据类型的解决方案，但都没有效果。有什么建议吗？我不能谈论你正在做的计算，但你似乎只是想安排组的组合。问题是它们是定向的还是无向的——也就是说，您需要计算流（A，B）和流（B，A），还是只计算一个 如果只有一个，您可以这样做：
for i,ward_list in enumerate(idgroups):
for j,ward_list2 in enumerate(idgroups[i:],start=i):
0,0 0,1 0,2 ... 0,n
1,1 1,2 ... 1,n
2,2 ... 2,n
流的函数中，并使用反向参数调用它，如图所示。；-）
更新
让我们定义一个名为flows
的函数：
def flows():
pass
现在，参数是什么
好吧，看看你的代码，它从一个数据帧中获取数据。你想要两个不同的病房，让我们从这些开始。结果似乎是结果网格的总和
def flows(df, ward_a, ward_b):
"""Return the sum of all the cells in the row/column intersections
of ward_a and ward_b."""
return 0
现在我将复制您的代码行：
ward_list = idgroups[index]
print ward_list
df6 = mergedcsv.loc[ward_list] #select rows with values in the list
dfcols = mergedcsv.loc[ward_list, :] #select columns with values in list
ward_liststr = map(str, ward_list) #convert ward_list to strings so that they can be used to select columns, won't work as integers.
ward_listint = map(int, ward_list)
#dfrowscols = mergedcsv.loc[ward_list, ward_listint]
df7 = df6.loc[:, ward_liststr]
print df7
regflowsum = df7.values.sum() #sum all values in dataframe
intflow = [regflowsum]
print intflow
我认为这是这里的大部分流
功能。让我们看看
ward_列表
显然是ward_a
或ward_b
参数我不确定什么是df6
，因为您可以在df7
中重新计算它。因此，这需要澄清
regflowsum
是我们想要的输出，我想 w=pysal.rook_from_shapefile("C:/Temp/AllNI/NIW01_sort.shp",idVariable='LABEL')
Simil = pysal.open("C:/Temp/AllNI/simNI.csv")
Similarity = np.array(Simil)
db = pysal.open('C:\Temp\SQLite\MatrixCSV2.csv', 'r')
dbf = pysal.open(r'C:\Temp\AllNI\NIW01_sortC.dbf', 'r')
ids = np.array((dbf.by_col['LABEL']))
commuters = np.array((dbf.by_col['Total'],dbf.by_col['IDNO']))
commutersint = commuters.astype(int)
comm = commutersint[0]
floor = int(MIN_COM_CT + 100)
solution = pysal.region.Maxp(w=w,z=Similarity,floor=floor,floor_variable=comm)
regions = solution.regions
#print regions
writecsv = r"C:\Temp\AllNI\reg_output.csv"
csv = open(writecsv,'w')
csv.write('"LABEL","REG_ID"\n')
for i in range(len(regions)):
for lines in regions[i]:
csv.write('"' + lines + '","' + str(i+1) + '"\n')
csv.close()
flows = r"C:\Temp\SQLite\MatrixCSV2.csv"
regs = r"C:\Temp\AllNI\reg_output.csv"
wardflows = pd.read_csv(flows)
regoutput = pd.read_csv(regs)
merged = pd.merge(wardflows, regoutput)
#duplicate REG_ID column as the index to be used later
merged['REG_ID2'] = merged['REG_ID']
merged.to_csv("C:\Temp\AllNI\merged.csv", index=False)
mergedcsv = pd.read_csv("C:\Temp\AllNI\merged.csv",index_col='WardID_1') #index this dataframe using the WardID_1 column
flabelList = pd.read_csv("C:\Temp\AllNI\merged.csv", usecols = ["WardID", "REG_ID"]) #create list of all FLabel values
reg_id = "REG_ID"
ward_flows = "RegIntFlows"
flds = [reg_id, ward_flows] #create list of fields to be use in search
dict_ref = {} # create a dictionary with for each REG_ID a list of corresponding FLABEL fields
#group the dataframe by the REG_ID column
idgroups = flabelList.groupby('REG_ID')['WardID'].apply(lambda x: x.tolist())
print idgroups
idgrp_df = pd.DataFrame(idgroups)
csvcols = mergedcsv.columns
#create a list of column names to pass as an index to select columns
columnlist = list(mergedcsv.columns.values)
mergedcsvgroup = mergedcsv.groupby('REG_ID').sum()
mergedcsvgroup.describe()
idList = idgroups[2]
df4 = pd.DataFrame()
df5 = pd.DataFrame()
col_ids = idList #ward id no
regiddf = idgroups.index.get_values()
print regiddf
#total number of region ids
#print regiddf
#create pairlist combinations from region ids
#combinations with replacement allows for repeated items
#pairs = list(itertools.combinations_with_replacement(regiddf, 2))
pairs = list(itertools.product(regiddf, repeat=2))
#print len(pairs)
#create a new dataframe with pairlists and summed data
pairlist = pd.DataFrame(pairs,columns=['origID','destID'])
print pairlist.tail()
header_pairlist = ["origID","destID","flow"]
header_intflow = ["RegID", "RegID2", "regflow"]
dfflows = pd.DataFrame(columns=header_intflow)
print mergedcsv.index
print mergedcsv.dtypes
#mergedcsv = mergedcsv.select_dtypes(include=['int64'])
#print mergedcsv.columns
#mergedcsv.rename(columns = lambda x: int(x), inplace=True)
def flows():
pass
#def flows(mergedcsv, region_a, region_b):
def flows(mergedcsv, ward_lista, ward_listb):
"""Return the sum of all the cells in the row/column intersections
of ward_lista and ward_listb."""
mergedcsv = mergedcsv.loc[:, mergedcsv.dtypes == 'int64']
regionflows = mergedcsv.loc[ward_lista, ward_listb]
regionflowsum = regionflows.values.sum()
#grid = [ax, bx, regflowsuma, regflowsumb]
gridoutput = [ax, bx, regionflowsum]
print gridoutput
return regflowsuma
return regflowsumb
#print mergedcsv.index
#mergedcsv.columns = mergedcsv.columns.str.strip()
for ax, group_a in enumerate(idgroups):
ward_lista = map(int, group_a)
print ward_lista
for bx, group_b in enumerate(idgroups[ax:], start=ax):
ward_listb = map(int, group_b)
#print ward_listb
flow_ab = flows(mergedcsv, ward_lista, ward_listb)
#flow_ab = flows(mergedcsv, group_a, group_b)
def flows(df, ward_a, ward_b):
"""Return the sum of all the cells in the row/column intersections
of ward_a and ward_b."""
print "Computing flows from:"
print " ", ward_a
print ""
print "flows into:"
print " ", ward_b
# Filter rows by ward_a, cols by ward_b:
grid = df.loc[ward_a, ward_b]
print "Grid:"
print grid
flowsum = grid.values.sum()
print "Flows:", flowsum
return flowsum
现在，我假设ward_a
和ward_b
值的格式已经正确。因此，我们必须str
-对它们或函数之外的任何内容进行验证。让我们这样做：
for ax, group_a in enumerate(idgroups):
ward_a = map(str, group_a)
for bx, group_b in enumerate(idgroups[ax:], start=ax):
ward_b = map(str, group_b)
flow_ab = flows(mergedcsv, ward_a, ward_b)
if ax != bx:
flow_ba = flows(mergedcsv, ward_b, ward_a)
else:
flow_ba = flow_ab
# Now what?
此时，您有两个数字。当病房相同（内部流量？）时，它们将相等。此时，您的原始代码不再有用，因为它只处理内部流，而不是A->B流，所以我不知道该怎么做。但是值在变量中，所以…Austin，谢谢。这是一个很大的帮助。我希望计算流向A到B和B到A的流量。。我没有遇到过flows函数，所以我们将对此进行研究。没有flows函数。奥斯汀，你的建议真的很有帮助。添加流函数是非常合乎逻辑的。我已经根据你的建议更新了代码。我似乎有数据类型错误或索引错误。我尝试了很多方法来解决这个问题，包括映射到int和选择int64类型的所有列，但仍然有错误。你能发现任何明显的错误吗？非常感谢您的建议您确认这些值实际上在列中了吗？有没有可能他们只在一排？是否尝试打印属性返回的列表？