ExcelとJSONファイルの読み込み

import pandas as pd

# The three most common load functions share the same philosophy
df_csv   = pd.read_csv('data.csv')
df_excel = pd.read_excel('data.xlsx')
df_json  = pd.read_json('data.json')

# Install the required engine:
# pip install openpyxl          # for .xlsx (modern)
# pip install xlrd==1.2.0       # for .xls (legacy)

import pandas as pd
df = pd.read_excel('report.xlsx', engine='openpyxl')

import pandas as pd

# Read the second sheet
df = pd.read_excel('workbook.xlsx', sheet_name=1)

# Read by name
df = pd.read_excel('workbook.xlsx', sheet_name='Sales')

# Inspect available sheets
xl = pd.ExcelFile('workbook.xlsx')
print(xl.sheet_names)  # ['Summary', 'Sales', 'Costs']

import pandas as pd

df = pd.read_excel(
    'sales_report.xlsx',
    sheet_name='Q1',
    header=2,          # header is on row 3 (0-indexed)
    usecols='A:D',     # Excel column range
    skiprows=[3, 4],   # skip rows 4 and 5
    nrows=100
)

import pandas as pd

# REST API response: list of records
json_str = '[{"name": "Alice", "age": 30}, {"name": "Bob", "age": 25}]'
df = pd.read_json(json_str, orient='records')
print(df)

import pandas as pd
from pandas.io.json import json_normalize

# From a file
df = pd.read_json('events.json')

# Flatten nested JSON
nested = [{'id': 1, 'user': {'name': 'A', 'age': 30}},
          {'id': 2, 'user': {'name': 'B', 'age': 25}}]
df_flat = json_normalize(nested)
print(df_flat.columns.tolist())  # ['id', 'user.name', 'user.age']

import pandas as pd

# file.jsonl contains one JSON record per line:
# {"id": 1, "event": "click"}
# {"id": 2, "event": "view"}
df = pd.read_json('events.jsonl', lines=True)
print(df)

import pandas as pd

# Unix milliseconds timestamp column
df = pd.read_json('events.json', orient='records')
df['created_at'] = pd.to_datetime(df['created_at'], unit='ms')
print(df['created_at'].dtype)  # datetime64[ns]

import pandas as pd

# Excel date stored as float (Excel serial date)
df = pd.read_excel('old_report.xls')
# If dates appear as floats (e.g., 44927.0), convert:
# from xlrd import xldate_as_datetime
# df['date'] = df['date'].apply(lambda x: xldate_as_datetime(x, 0))

import pandas as pd

with pd.ExcelFile('annual_report.xlsx') as xf:
    df_q1 = xf.parse('Q1')
    df_q2 = xf.parse('Q2')

print(df_q1.shape, df_q2.shape)

import pandas as pd
import requests

response = requests.get('https://api.example.com/records')
data = response.json()   # Python list of dicts
df = pd.DataFrame(data)
print(df.head())