5 أسرار غير معروفة للباندا

1. نطاقات التواريخ [نطاقات التواريخ]

date_from = "2019-01-01"
date_to = "2019-01-12"
date_range = pd.date_range(date_from, date_to, freq="D")
date_range

for i, (date_from, date_to) in enumerate(zip(date_range[:-1], date_range[1:]), 1):
   date_from = date_from.date().isoformat()
   date_to = date_to.date().isoformat()
   print("%d. date_from: %s, date_to: %s" % (i, date_from, date_to))

1. date_from: 2019-01-01, date_to: 2019-01-02
2. date_from: 2019-01-02, date_to: 2019-01-03
3. date_from: 2019-01-03, date_to: 2019-01-04
4. date_from: 2019-01-04, date_to: 2019-01-05
5. date_from: 2019-01-05, date_to: 2019-01-06
6. date_from: 2019-01-06, date_to: 2019-01-07
7. date_from: 2019-01-07, date_to: 2019-01-08
8. date_from: 2019-01-08, date_to: 2019-01-09
9. date_from: 2019-01-09, date_to: 2019-01-10
10. date_from: 2019-01-10, date_to: 2019-01-11
11. date_from: 2019-01-11, date_to: 2019-01-12

2. الدمج مع مؤشر المصدر [الدمج مع المؤشر]

left = pd.DataFrame({"key": ["key1", "key2", "key3", "key4"], "value_l": [1, 2, 3, 4]})

right = pd.DataFrame({"key": ["key3", "key2", "key1", "key6"], "value_r": [3, 2, 1, 6]})

df_merge = left.merge(right, on='key', how='left', indicator=True)

df_merge._merge.value_counts()

both          3
left_only     1
right_only    0
Name: _merge, dtype: int64

3. الدمج بأقرب قيمة [الدمج الأقرب]

quotes = pd.DataFrame(
   [
       ["2016-05-25 13:30:00.023", "GOOG", 720.50, 720.93],
       ["2016-05-25 13:30:00.023", "MSFT", 51.95, 51.96],
       ["2016-05-25 13:30:00.030", "MSFT", 51.97, 51.98],
       ["2016-05-25 13:30:00.041", "MSFT", 51.99, 52.00],
       ["2016-05-25 13:30:00.048", "GOOG", 720.50, 720.93],
       ["2016-05-25 13:30:00.049", "AAPL", 97.99, 98.01],
       ["2016-05-25 13:30:00.072", "GOOG", 720.50, 720.88],
       ["2016-05-25 13:30:00.075", "MSFT", 52.01, 52.03],
   ],
   columns=["timestamp", "ticker", "bid", "ask"],
)
quotes['timestamp'] = pd.to_datetime(quotes['timestamp'])

trades = pd.DataFrame(
   [
       ["2016-05-25 13:30:00.023", "MSFT", 51.95, 75],
       ["2016-05-25 13:30:00.038", "MSFT", 51.95, 155],
       ["2016-05-25 13:30:00.048", "GOOG", 720.77, 100],
       ["2016-05-25 13:30:00.048", "GOOG", 720.92, 100],
       ["2016-05-25 13:30:00.048", "AAPL", 98.00, 100],
   ],
   columns=["timestamp", "ticker", "price", "quantity"],
)
trades['timestamp'] = pd.to_datetime(trades['timestamp'])

pd.merge_asof(trades, quotes, on="timestamp", by='ticker', tolerance=pd.Timedelta('10ms'), direction='backward')

4. إنشاء تقرير Excel

df = pd.DataFrame(pd.np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), columns=["a", "b", "c"])

report_name = 'example_report.xlsx'
sheet_name = 'Sheet1'
writer = pd.ExcelWriter(report_name, engine='xlsxwriter')
df.to_excel(writer, sheet_name=sheet_name, index=False)
# writer.save()

#   (workbook)
workbook = writer.book
worksheet = writer.sheets[sheet_name]
#   
chart = workbook.add_chart({'type': 'line'})
#       ,
#      /:
#     [sheetname, first_row, first_col, last_row, last_col]
chart.add_series({
   'categories': [sheet_name, 1, 0, 3, 0],
   'values':     [sheet_name, 1, 1, 3, 1],
})
#   
chart.set_x_axis({'name': 'Index', 'position_axis': 'on_tick'})
chart.set_y_axis({'name': 'Value', 'major_gridlines': {'visible': False}})
#    
worksheet.insert_chart('E2', chart)
#  
writer.save()

5. توفير مساحة القرص

df = pd.DataFrame(pd.np.random.randn(50000,300))

df.to_csv('random_data.csv', index=False)

df.to_csv('random_data.gz', compression='gzip', index=False)

df = pd.read_csv('random_data.gz')

استنتاج