To read dataframe, just use pandas.read.....() functions, then convert to datar tibble if needed.¶

In [13]:

import datar.all as dr
import pandas as pd
from pathlib import Path

pd.set_option("display.width", 200)

# Get the path object pointing to the ``notebooks`` directory that contains *.csv files 
data_dir = next(Path("/home").rglob("*/notebooks/*.csv")).parent

import datar.all as dr import pandas as pd from pathlib import Path pd.set_option("display.width", 200) # Get the path object pointing to the ``notebooks`` directory that contains *.csv files data_dir = next(Path("/home").rglob("*/notebooks/*.csv")).parent

1. Read from CSV file¶

In [10]:

tb_csv = dr.tibble(pd.read_csv(data_dir/'air_quality_no2_long.csv'))

print(tb_csv.head())

tb_csv = dr.tibble(pd.read_csv(data_dir/'air_quality_no2_long.csv')) print(tb_csv.head())

    city country                   date.utc location parameter     value   unit
   <str>   <str>                      <str>    <str>     <str> <float64>  <str>
0  Paris      FR  2019-06-21 00:00:00+00:00  FR04014       no2      20.0  µg/m³
1  Paris      FR  2019-06-20 23:00:00+00:00  FR04014       no2      21.8  µg/m³
2  Paris      FR  2019-06-20 22:00:00+00:00  FR04014       no2      26.5  µg/m³
3  Paris      FR  2019-06-20 21:00:00+00:00  FR04014       no2      24.9  µg/m³
4  Paris      FR  2019-06-20 20:00:00+00:00  FR04014       no2      21.4  µg/m³

2. Read from Excel file¶

In [11]:

tb_excel = dr.tibble(pd.read_excel(data_dir/"emp_sheetname.xlsx", sheet_name='emp'))

print(tb_excel)

tb_excel = dr.tibble(pd.read_excel(data_dir/"emp_sheetname.xlsx", sheet_name='emp')) print(tb_excel)

        id      name    salary       start_date        dept
  <object>     <str> <float64> <datetime64[us]>       <str>
0        1      Rick    623.30       2012-01-01          IT
1        2       Dan    515.20       2013-09-23  Operations
2        3  Michelle    611.00       2014-11-15          IT
3        4      Ryan    729.00       2014-05-11          HR
4               Gary    843.25       2015-03-27     Finance
5        6      Nina    578.00       2013-05-21          IT
6        7     Simon    632.80       2013-07-30  Operations
7        8      Guru    722.50       2014-06-17     Finance

3 .Read with more options¶

In [14]:

tb_pokemon = dr.tibble(
    pd.read_csv(
        filepath_or_buffer=data_dir/"pokemon.csv",
        dtype={
            "Type 1": "category",
            "Type 2": "category",
            "Generation": "category",
            "Legendary": "bool"
        }
    )
    .drop(columns=["#"])
    .pipe(lambda f: f.set_axis(f.columns.str.strip().str.replace(r"\s+", "_", regex=True).str.replace(".", ""), axis=1))
    .assign(Generation = pd.col('Generation').cat.as_ordered())
)

print(
    tb_pokemon
    >> dr.slice_head(n=5)
)

tb_pokemon = dr.tibble( pd.read_csv( filepath_or_buffer=data_dir/"pokemon.csv", dtype={ "Type 1": "category", "Type 2": "category", "Generation": "category", "Legendary": "bool" } ) .drop(columns=["#"]) .pipe(lambda f: f.set_axis(f.columns.str.strip().str.replace(r"\s+", "_", regex=True).str.replace(".", ""), axis=1)) .assign(Generation = pd.col('Generation').cat.as_ordered()) ) print( tb_pokemon >> dr.slice_head(n=5) )

                    Name     Type_1     Type_2   Total      HP  Attack  Defense  Sp_Atk  Sp_Def   Speed Generation  Legendary
                   <str> <category> <category> <int64> <int64> <int64>  <int64> <int64> <int64> <int64> <category>     <bool>
0              Bulbasaur      Grass     Poison     318      45      49       49      65      65      45          1      False
1                Ivysaur      Grass     Poison     405      60      62       63      80      80      60          1      False
2               Venusaur      Grass     Poison     525      80      82       83     100     100      80          1      False
3  VenusaurMega Venusaur      Grass     Poison     625      80     100      123     122     120      80          1      False
4             Charmander       Fire        NaN     309      39      52       43      60      50      65          1      False