How do I rename columns in a python pandas dataframe?

Question

i'm new to pandas and was wondering if someone can help me out.

• i have written the code shown below.
• the contents of the json files are pasted below the script.
• below the json contents we can see the script output.

i would simply like to set the name of each column in the output dataframe as the name of the country object (eg. Germany or France)

instead of getting this output

                  value    name        value     name
tag                                                  
capital           Paris  France       Berlin  Germany
population  34111000000  France  11233000000  Germany
language         French  France       German  Germany

...i would like something like this

                  France             Germany     
tag                                                  
capital           Paris         Berlin  Germany
population  34111000000    11233000000  Germany
language         French         German  Germany

any help would be appreciated : - )

here is my code...

import numpy as np
import pandas as pd
import json

class Country(object):
    def __init__(self,name):
        self.name = name
        self.json = name + "_Data.json"

def ImportJson(x):
    ImportedJson = []
    for country in x:
        with open(country.json) as country_json_file:
            country_data = json.load(country_json_file)
            country_data_table = pd.DataFrame(country_data['data'], columns=['tag', 'value']).set_index('tag')
            country_data_table['name'] = country.name
        ImportedJson.append(country_data_table)
    return ImportedJson

France = Country("France")
Germany = Country("Germany")
All_Countries = [France,Germany]

OpenedJson = ImportJson(All_Countries)

Country_Data = pd.concat(OpenedJson,axis=1)
print Country_Data

here are the json files

Germany_Data.json

{
    "data": [
        {
            "tag": "capital",
            "value": "Berlin"
        },
        {
            "tag": "population",
            "value": 11233000000
        },
        {
            "tag": "language",
            "value": "German"
        }
    ],
    "result_count": 33,
    "page_size": 5000,
    "current_page": 1,
    "total_pages": 1,
    "api_call_credits": 1
}

France_Data.json

{
    "data": [
        {
            "tag": "capital",
            "value": "Paris"
        },
        {
            "tag": "population",
            "value": 34111000000
        },
        {
            "tag": "language",
            "value": "French"
        }
    ],
    "result_count": 33,
    "page_size": 5000,
    "current_page": 1,
    "total_pages": 1,
    "api_call_credits": 1
}

script output

                  value    name        value     name
tag                                                  
capital           Paris  France       Berlin  Germany
population  34111000000  France  11233000000  Germany
language         French  France       German  Germany

Answer 1

In your function ImportJson you have the following two lines of code.

country_data_table = pd.DataFrame(country_data['data'], columns=['tag', 'value']).set_index('tag')
country_data_table['name'] = country.name

Delete the second line and add this directly after it

country_data_table.rename(columns={'value':country.name}, inplace=True)

Answer 2

I rewrote your class

import numpy as np
import pandas as pd
import json

class Country(object):
    def __init__(self,name):
        self.name = name
        self.json = name + "_Data.json"
        with open(self.json, 'r') as fp:
            self.data = json.load(fp)['data']
        self.series = pd.DataFrame.from_records(
            self.data
        ).set_index('tag').value.rename(self.name)

France = Country("France")
Germany = Country("Germany")


pd.concat([c.series for c in [France, Germany]], axis=1)

                 France      Germany
tag                                 
capital           Paris       Berlin
population  34111000000  11233000000
language         French       German

---

if you insisted on manipulating your constructed dataframe

# take transpose so I can groupby index and add a count column
# for each `name` and `value`.  Once I have a unique index, I can
# do more.
CD1 = Country_Data.T.set_index(
    Country_Data.T.groupby(level=0).cumcount(), append=True).T

# strategy is to filter `value` columns and reassign the columns
CD2 = CD1.filter(like='value')
CD2.columns = Country_Data.loc['capital', 'name'].tolist()

CD2

                 France      Germany
tag                                 
capital           Paris       Berlin
population  34111000000  11233000000
language         French       German

---

setup json files

import json

with open('Germany_Data.json', 'w') as fp:
    json.dump(
        {
            "data": [
                {
                    "tag": "capital",
                    "value": "Berlin"
                },
                {
                    "tag": "population",
                    "value": 11233000000
                },
                {
                    "tag": "language",
                    "value": "German"
                }
            ],
            "result_count": 33,
            "page_size": 5000,
            "current_page": 1,
            "total_pages": 1,
            "api_call_credits": 1
        }
        , fp)

with open('France_Data.json', 'w') as fp:
    json.dump(
        {
            "data": [
                {
                    "tag": "capital",
                    "value": "Paris"
                },
                {
                    "tag": "population",
                    "value": 34111000000
                },
                {
                    "tag": "language",
                    "value": "French"
                }
            ],
            "result_count": 33,
            "page_size": 5000,
            "current_page": 1,
            "total_pages": 1,
            "api_call_credits": 1
        }
        , fp)