Python 熊猫：基于两个不同的列创建唯一值的索引
我正在为一个创建航道的项目改进代码。我目前拥有的是由c_match的索引值组合在一起的数据帧。很酷，很好，乍一看一切都是正确的 航道是一组具有相同折扣和最低收费的州。我的代码返回具有相同折扣的状态。大多数有相同折扣的州也有相同的最低收费。然而，异常值是具有相同折扣和不同最低费用的状态 目标：创建具有相同最低费用和相同折扣百分比的航线 我的想法是：创建一个逻辑操作，将具有相同费率和成本的州名称关联起来，并返回它们的费率和成本。对于同一费率有不同费用的国家仍然需要加以说明 期望输出：Python 熊猫：基于两个不同的列创建唯一值的索引,python,pandas,dataframe,logic,data-science,Python,Pandas,Dataframe,Logic,Data Science,我正在为一个创建航道的项目改进代码。我目前拥有的是由c_match的索引值组合在一起的数据帧。很酷，很好，乍一看一切都是正确的 航道是一组具有相同折扣和最低收费的州。我的代码返回具有相同折扣的状态。大多数有相同折扣的州也有相同的最低收费。然而，异常值是具有相同折扣和不同最低费用的状态 目标：创建具有相同最低费用和相同折扣百分比的航线 我的想法是：创建一个逻辑操作，将具有相同费率和成本的州名称关联起来，并返回它们的费率和成本。对于同一费率有不同费用的国家仍然需要加以说明 期望输出： Shippin
Shipping Lane Rate Cost
20_21_RDWY_Purple_AL_AR_KY_LA_MS_SC_TN_PE 50.80% 120
20_21_RDWY_Purple_AZ 50.80% 155
20_21_RDWY_Purple_CA 62.40% 145
20_21_RDWY_Purple_CO_ND_WY_MB_NF_PQ 62.40% 155
20_21_RDWY_Purple_CT_DE_MN_NE 50.00% 145
20_21_RDWY_Purple_DC_IA_KS_MD_MI_OH_OK_WI 49.00% 125
20_21_RDWY_Purple_FL 48.30% 125
def remove_dups(input, output):
input.sort()
n_list = list(input for input, _ in itertools.groupby(input))
output.append(n_list)
def get_matches_discount(state):
state_groups = []
state_rates = []
state_cost = []
final_format = []
match = []
c_match = []
for i, x in enumerate(df_d[state]):
#checks within the column for identical values then maps where the identical values are
match1 = [j for j, y in enumerate(df_d[state].isin([x])) if y is True]
match.append(match1)
remove_dups(match, c_match)
for list in c_match:
for elements in list:
r = elements[0]
state_g = df_d.index[elements]
state_groups.append(state_g)
state_r = df_d[state][r]
state_rates.append(state_r)
print(state_rates)
match_cost = df_m[state][r]
state_cost.append(match_cost)
for i in state_groups:
delimiter = "_"
join_str = delimiter.join(i)
j_str = "20_21_RDWY_Purple_" + join_str
final_format.append(j_str)
master_frame = pd.DataFrame(
{'Shipping Lane': final_format,
'Rate': state_rates,
'Cost': state_cost,
}
)
print(master_frame)
return master_frame
m_col_names = ['AL', 'AR', 'AZ', 'CA', 'CO', 'CT', 'DC', 'DE', 'FL', 'GA', 'IA', 'ID', 'IL', 'IN', 'KS', 'KY', 'LA',
'MA', 'MD', 'ME', 'MI', 'MN', 'MO', 'MS', 'MT', 'NC', 'ND', 'NE', 'NH', 'NJ', 'NM', 'NV', 'NY', 'OH',
'OK', 'OR', 'PA', 'RI', 'SC', 'SD', 'TN', 'TX', 'UT', 'VA', 'VT', 'WA', 'WI', 'WV', 'WY', 'AB', 'BC',
'MB', 'NB', 'NF', 'NS', 'ON', 'PE', 'PQ', 'SK']
# calls the function in a loop to process one column at a time
# creates the master data frame outside of the function calling for loop
master_dataframe0 = pd.DataFrame()
for state in m_col_names:
temp_df = get_matches_discount(state)
# Stores the function call as a variable
master_dataframe0 = master_dataframe0.append(temp_df)
# Creates an appended dataframe outside of the function
print(master_dataframe0)
master_dataframe0.to_excel("shipping_lanes_revised00.xlsx")
State AL AR AZ CA CO CT DC
AL 120.00 120.00 155.00 145.00 155.00 145.00 125.00
AR 120.00 120.00 155.00 155.00 145.00 155.00 145.00
AZ 155.00 155.00 120.00 120.00 125.00 185.00 185.00
CA 145.00 164.30 120.00 120.00 170.00 185.00 185.00
CO 155.00 145.00 125.00 145.00 120.00 155.00 155.00
CT 145.00 155.00 185.00 185.00 155.00 120.00 120.00
DC 125.00 155.00 185.00 185.00 155.00 120.00 185.00
DE 145.00 155.00 185.00 185.00 155.00 120.00 120.00
FL 125.00 145.00 145.00 185.00 145.00 155.00 145.00
GA 120.00 120.00 155.00 145.00 155.00 145.00 120.00
IA 125.00 125.00 155.00 145.00 125.00 155.00 145.00
ID 145.00 155.00 145.00 145.00 125.00 185.00 185.00
IL 120.00 120.00 155.00 145.00 145.00 125.00 125.00
IN 120.00 120.00 155.00 145.00 145.00 125.00 120.00
KS 125.00 120.00 155.00 155.00 120.00 155.00 145.00
KY 120.00 120.00 155.00 145.00 145.00 125.00 125.00
LA 120.00 120.00 155.00 145.00 155.00 155.00 155.00
MA 155.00 155.00 185.00 185.00 145.00 120.00 120.00
MD 125.00 145.00 185.00 185.00 155.00 120.00 120.00
ME 155.00 155.00 185.00 185.00 145.00 120.00 125.00
MI 125.00 125.00 145.00 145.00 155.00 125.00 120.00
MN 145.00 125.00 155.00 145.00 145.00 155.00 145.00
MO 120.00 120.00 155.00 155.00 125.00 145.00 145.00
MS 120.00 120.00 155.00 155.00 145.00 155.00 145.00
MT 145.00 155.00 155.00 155.00 125.00 185.00 185.00
NC 120.00 125.00 145.00 185.00 155.00 125.00 120.00
ND 155.00 155.00 145.00 145.00 155.00 155.00 155.00
NE 145.00 125.00 155.00 155.00 120.00 155.00 155.00
NH 155.00 155.00 185.00 185.00 145.00 120.00 120.00
NJ 145.00 155.00 185.00 185.00 155.00 120.00 120.00
NM 155.00 125.00 120.00 145.00 120.00 145.00 145.00
NV 145.00 155.00 120.00 120.00 145.00 185.00 185.00
NY 145.00 145.00 185.00 185.00 155.00 120.00 120.00
OH 125.00 125.00 145.00 145.00 155.00 120.00 120.00
OK 125.00 120.00 145.00 155.00 120.00 155.00 155.00
OR 185.00 145.00 155.00 125.00 155.00 185.00 185.00
PA 145.00 145.00 185.00 185.00 155.00 120.00 120.00
RI 155.00 155.00 185.00 185.00 145.00 120.00 120.00
SC 120.00 120.00 145.00 185.00 155.00 125.00 120.00
SD 155.00 145.00 155.00 155.00 120.00 155.00 145.00
TN 120.00 120.00 155.00 145.00 155.00 145.00 125.00
TX 125.00 120.00 145.00 155.00 125.00 145.00 155.00
UT 170.00 164.30 132.50 132.50 127.20 145.00 145.00
VA 120.00 145.00 145.00 185.00 155.00 120.00 120.00
State AL AR AZ CA CO CT DC
AL 50.80% 44.10% 54.30% 73.10% 53.90% 50.00% 49.00%
AR 50.80% 50.80% 53.90% 65.70% 50.00% 53.90% 50.00%
AZ 56.70% 55.80% 50.80% 54.10% 49.60% 59.50% 64.40%
CA 62.40% 61.00% 54.30% 61.40% 43.00% 52.30% 54.30%
CO 54.30% 67.10% 49.00% 65.70% 50.80% 54.30% 54.30%
CT 50.00% 53.90% 64.40% 72.50% 54.30% 50.80% 50.80%
DC 49.00% 53.90% 64.40% 64.40% 54.30% 50.80% 64.40%
DE 50.00% 53.90% 64.40% 64.40% 54.30% 50.80% 50.80%
FL 48.30% 35.00% 55.50% 55.50% 55.10% 66.40% 62.30%
GA 67.90% 44.10% 71.00% 64.60% 56.00% 50.00% 44.10%
IA 49.00% 49.00% 54.30% 61.80% 49.00% 53.90% 50.00%
ID 61.80% 54.30% 50.00% 75.90% 49.00% 64.40% 64.40%
IL 44.10% 44.10% 54.30% 64.00% 50.00% 49.00% 49.00%
IN 44.10% 1.60% 11.70% 26.10% -0.70% 49.00% 44.10%
KS 49.00% 63.40% 61.00% 67.70% 72.50% 72.20% 50.00%
KY 50.80% 44.10% 54.30% 61.50% 50.00% 49.00% 49.00%
LA 50.80% 44.10% 54.30% 61.80% 53.90% 54.30% 53.90%
MA 63.50% 53.90% 67.70% 63.90% 53.00% 63.50% 44.10%
MD 49.00% 50.00% 64.40% 73.80% 54.30% 50.80% 50.80%
ME 53.90% 54.30% 64.40% 64.40% 61.80% 50.80% 49.00%
MI 49.00% 49.00% 61.80% 55.10% 53.90% 49.00% 44.10%
MN 50.00% 49.00% 54.30% 61.80% 50.00% 53.90% 50.00%
MO 44.10% 50.80% 53.90% 56.10% 49.00% 50.00% 50.00%
MS 50.80% 50.80% 54.30% 63.90% 50.00% 53.90% 50.00%
MT 61.80% 54.30% 53.90% 75.80% 49.00% 64.40% 64.40%
NC 44.10% 59.20% 53.50% 58.60% 57.90% 42.90% 69.60%
ND 54.30% 53.90% 61.80% 61.80% 54.30% 53.90% 53.90%
NE 50.00% 49.00% 54.30% 54.30% 44.10% 53.90% 53.90%
NH 53.90% 54.30% 64.40% 64.40% 61.80% 50.80% 44.10%
NJ 50.50% 51.50% 70.50% 66.20% 59.70% 67.10% 50.80%
NM 53.90% 49.00% 44.10% 68.20% 44.10% 61.80% 61.80%
NV 61.80% 54.30% 52.70% 73.50% 50.00% 64.40% 64.40%
NY 61.10% 69.00% 65.50% 68.90% 63.00% 68.40% 50.80%
OH 49.00% 49.00% 68.50% 71.50% 72.30% 60.70% 44.10%
OK 49.00% 50.80% 50.00% 54.30% 44.10% 54.30% 54.30%
OR 64.40% 61.80% 53.90% 64.00% 53.90% 64.40% 64.40%
PA 47.20% 57.00% 33.70% 51.90% 45.50% 50.80% 50.80%
RI 53.90% 54.30% 64.40% 64.40% 61.80% 50.80% 44.10%
SC 50.80% 44.10% 61.80% 58.70% 54.30% 49.00% 44.10%
SD 53.90% 50.00% 54.30% 54.30% 44.10% 54.30% 61.80%
TN 50.80% 50.80% 52.50% 62.60% 61.30% 53.30% 49.00%
TX 56.60% 46.00% 51.40% 58.30% 53.20% 63.10% 65.10%
UT 45.00% 60.60% 73.50% 73.50% 70.30% 44.40% 61.90%
VA 57.90% 50.00% 61.80% 72.10% 54.30% 44.10% 50.80%
Shipping Lane Rate Cost
0 20_21_RDWY_Purple_AL_AR_KY_LA_MS_SC_TN_PE 50.80% 120.0
1 20_21_RDWY_Purple_AZ 56.70% 155.0
2 20_21_RDWY_Purple_CA 62.40% 145.0
3 20_21_RDWY_Purple_CO_ND_WY_MB_NF_PQ 54.30% 155.0
4 20_21_RDWY_Purple_CT_DE_MN_NE 50.00% 145.0
5 20_21_RDWY_Purple_DC_IA_KS_MD_MI_OH_OK_WI 49.00% 125.0
6 20_21_RDWY_Purple_FL 48.30% 125.0
7 20_21_RDWY_Purple_GA 67.90% 120.0
8 20_21_RDWY_Purple_ID_MT_NV_AB_SK 61.80% 145.0
9 20_21_RDWY_Purple_IL_IN_MO_NC_WV 44.10% 120.0
10 20_21_RDWY_Purple_MA 63.50% 155.0
11 20_21_RDWY_Purple_ME_NH_NM_RI_SD_VT_NB_NS 53.90% 155.0
12 20_21_RDWY_Purple_NJ 50.50% 145.0
13 20_21_RDWY_Purple_NY 61.10% 145.0
14 20_21_RDWY_Purple_OR_WA_BC 64.40% 185.0
15 20_21_RDWY_Purple_PA 47.20% 145.0
16 20_21_RDWY_Purple_TX 56.60% 125.0
17 20_21_RDWY_Purple_UT 45.00% 170.0
18 20_21_RDWY_Purple_VA 57.90% 120.0
19 20_21_RDWY_Purple_ON 37.30% 145.0
0 20_21_RDWY_Purple_AL_GA_IL_KY_LA_SC 44.10% 120.0
1 20_21_RDWY_Purple_AR_MO_MS_OK_TN_NB_NF_NS_PE 50.80% 120.0
2 20_21_RDWY_Purple_AZ 55.80% 155.0
3 20_21_RDWY_Purple_CA 61.00% 164.3
4 20_21_RDWY_Purple_CO 67.10% 145.0
5 20_21_RDWY_Purple_CT_DC_DE_MA_ND_MB 53.90% 155.0
6 20_21_RDWY_Purple_FL 35.00% 145.0
7 20_21_RDWY_Purple_IA_MI_MN_NE_NM_OH_WI_WV 49.00% 125.0
8 20_21_RDWY_Purple_ID_ME_MT_NH_NV_RI_VT_PQ_SK 54.30% 155.0
9 20_21_RDWY_Purple_IN 1.60% 120.0
10 20_21_RDWY_Purple_KS 63.40% 120.0
11 20_21_RDWY_Purple_MD_SD_VA_WY 50.00% 145.0
12 20_21_RDWY_Purple_NC 59.20% 125.0
13 20_21_RDWY_Purple_NJ 51.50% 155.0
14 20_21_RDWY_Purple_NY 69.00% 145.0
15 20_21_RDWY_Purple_OR_WA_AB 61.80% 145.0
16 20_21_RDWY_Purple_PA 57.00% 145.0
17 20_21_RDWY_Purple_TX 46.00% 120.0
18 20_21_RDWY_Purple_UT 60.60% 164.3
19 20_21_RDWY_Purple_BC 64.40% 185.0
20 20_21_RDWY_Purple_ON 32.10% 145.0
0 20_21_RDWY_Purple_AL_CA_IA_IL_KY_LA_MN_MS_NE_SD_WA_AB_BC 54.30% 155.0
1 20_21_RDWY_Purple_AR_MO_MT_OR 53.90% 155.0
2 20_21_RDWY_Purple_AZ_NB_NF_NS_PE 50.80% 120.0
3 20_21_RDWY_Purple_CO 49.00% 125.0
4 20_21_RDWY_Purple_CT_DC_DE_MD_ME_NH_RI_VT_ON_PQ_SK 64.40% 185.0
5 20_21_RDWY_Purple_FL 55.50% 145.0
6 20_21_RDWY_Purple_GA 71.00% 155.0
7 20_21_RDWY_Purple_ID_OK_WY 50.00% 145.0
8 20_21_RDWY_Purple_IN 11.70% 155.0
9 20_21_RDWY_Purple_KS 61.00% 155.0
10 20_21_RDWY_Purple_MA 67.70% 185.0
11 20_21_RDWY_Purple_MI_ND_SC_VA_WV_MB 61.80% 145.0
12 20_21_RDWY_Purple_NC 53.50% 145.0
13 20_21_RDWY_Purple_NJ 70.50% 185.0
14 20_21_RDWY_Purple_NM 44.10% 120.0
15 20_21_RDWY_Purple_NV 52.70% 120.0
16 20_21_RDWY_Purple_NY 65.50% 185.0
17 20_21_RDWY_Purple_OH 68.50% 145.0
18 20_21_RDWY_Purple_PA 33.70% 185.0
19 20_21_RDWY_Purple_TN 52.50% 155.0
20 20_21_RDWY_Purple_TX 51.40% 145.0
状态有多行，但它们也在列上。看起来您只是在显示
ALState.groupby上合并RateCost.apply（lambda x:“'.join（x））状态有多行，但它们也在列上。看起来您只是在显示
ALState.groupby上合并RateCost.apply（lambda x:“'.join（x））通过Erickson对
.groupbypd.set_option('display.max_rows', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.width', None)
pd.set_option('display.max_colwidth', None)
df_d = pd.read_excel(path,
sheet_name=0,
header=0,
index_col=False,
keep_default_na=True)
df_m = pd.read_excel(path2,
sheet_name=0,
header=0,
index_col=False,
keep_default_na=True)
m_col_names = ['AL', 'AR', 'AZ', 'CA', 'CO', 'CT', 'DC', 'DE', 'FL', 'GA', 'IA', 'ID', 'IL', 'IN', 'KS', 'KY', 'LA',
'MA', 'MD', 'ME', 'MI', 'MN', 'MO', 'MS', 'MT', 'NC', 'ND', 'NE', 'NH', 'NJ', 'NM', 'NV', 'NY', 'OH',
'OK', 'OR', 'PA', 'RI', 'SC', 'SD', 'TN', 'TX', 'UT', 'VA', 'VT', 'WA', 'WI', 'WV', 'WY', 'AB', 'BC',
'MB', 'NB', 'NF', 'NS', 'ON', 'PE', 'PQ', 'SK']
final_frame = pd.DataFrame()
for state in m_col_names:
master_dataframe0 = (pd.merge(df_d[['State', state]], df_m[['State', state]], how='inner', on='State')
.rename({state + '_x': 'Rate', state + '_y': 'Cost'}, axis=1)
.groupby(['Rate', 'Cost'])['State'].apply(lambda x: '_'.join(x)).reset_index()
.sort_values('State'))
master_dataframe0['Origin'] = state
master_dataframe0 = master_dataframe0[['State', 'Rate', 'Cost', 'Origin']].assign(
State='20_21_RDWY_Purple_' + master_dataframe0['State'])
final_frame = final_frame.append(master_dataframe0)
print(final_frame)
final_frame.to_excel("w3llshipmeright.xlsx")
使用Erickson的帮助以及
.groupbypd.set_option('display.max_rows', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.width', None)
pd.set_option('display.max_colwidth', None)
df_d = pd.read_excel(path,
sheet_name=0,
header=0,
index_col=False,
keep_default_na=True)
df_m = pd.read_excel(path2,
sheet_name=0,
header=0,
index_col=False,
keep_default_na=True)
m_col_names = ['AL', 'AR', 'AZ', 'CA', 'CO', 'CT', 'DC', 'DE', 'FL', 'GA', 'IA', 'ID', 'IL', 'IN', 'KS', 'KY', 'LA',
'MA', 'MD', 'ME', 'MI', 'MN', 'MO', 'MS', 'MT', 'NC', 'ND', 'NE', 'NH', 'NJ', 'NM', 'NV', 'NY', 'OH',
'OK', 'OR', 'PA', 'RI', 'SC', 'SD', 'TN', 'TX', 'UT', 'VA', 'VT', 'WA', 'WI', 'WV', 'WY', 'AB', 'BC',
'MB', 'NB', 'NF', 'NS', 'ON', 'PE', 'PQ', 'SK']
final_frame = pd.DataFrame()
for state in m_col_names:
master_dataframe0 = (pd.merge(df_d[['State', state]], df_m[['State', state]], how='inner', on='State')
.rename({state + '_x': 'Rate', state + '_y': 'Cost'}, axis=1)
.groupby(['Rate', 'Cost'])['State'].apply(lambda x: '_'.join(x)).reset_index()
.sort_values('State'))
master_dataframe0['Origin'] = state
master_dataframe0 = master_dataframe0[['State', 'Rate', 'Cost', 'Origin']].assign(
State='20_21_RDWY_Purple_' + master_dataframe0['State'])
final_frame = final_frame.append(master_dataframe0)
print(final_frame)
final_frame.to_excel("w3llshipmeright.xlsx")
然后如何重命名每个州，而不仅仅是AL@AdamZuckerman输出是什么样子的？50列不同的费率和50列不同的成本？或者作为行，您可以将每一行分类为
AL-0_21_RDWY_Purple_AL_aru KY_LA_MS_SC_TNCA-20_21_RDWY_Purple_AZCA-0_21_RDWY_Purple_AL_KY_LA_MS_SC_TNAL-20_21_RDWY_Purple__AZ您可以从前缀栏中看出我所指的状态。无论哪种方式，我认为最好创建一个新的SO问题，它是这个问题的扩展，并具有所需的输出。您不必在列和行中显示所有50个状态，但可能只需显示几个，这样人们就有了想法。现在输出看起来很棒！我想出来了。简单的修正：。重命名（{state+''ux'：'Rate'，state+''uy'：'Cost'}，axis=1）然后如何重命名每个状态，而不仅仅是AL@AdamZuckerman输出是什么样子的？50列不同的费率和50列不同的成本？或者作为行，您可以将每一行分类为AL-0_21_RDWY_Purple_AL_aru KY_LA_MS_SC_TN
，CA-20_21_RDWY_Purple_AZ
，CA-0_21_RDWY_Purple_AL_KY_LA_MS_SC_TN
，AL-20_21_RDWY_Purple__AZ您可以从前缀栏中看出我所指的状态。无论哪种方式，我认为最好创建一个新的SO问题，它是这个问题的扩展，并具有所需的输出。您不必在列和行中显示所有50个状态，但可能只需显示几个，这样人们就有了想法。现在输出看起来很棒！我想出来了。简单修复：。重命名（{state+''ux'：'Rate'，state+''uy'：'Cost'}，axis=1）