In [1]:

    

import pandas as pd


    

In [2]:

    

df = pd.read_csv('data/src/sample_header_index_dtype.csv', index_col=0)
print(df)


    

    




       a    b      c  d
ONE    1    1  100.0  x
TWO    2   20    NaN  y
THREE  3  300  300.0  z

In [3]:

    

print(df.dtypes)


    

    




a      int64
b      int64
c    float64
d     object
dtype: object

In [4]:

    

print(df.applymap(type))


    

    




                   a              b                c              d
ONE    <class 'int'>  <class 'int'>  <class 'float'>  <class 'str'>
TWO    <class 'int'>  <class 'int'>  <class 'float'>  <class 'str'>
THREE  <class 'int'>  <class 'int'>  <class 'float'>  <class 'str'>

In [5]:

    

df_str = pd.read_csv('data/src/sample_header_index_dtype.csv',
                     index_col=0, dtype=str)
print(df_str)


    

    




       a    b    c  d
ONE    1  001  100  x
TWO    2  020  NaN  y
THREE  3  300  300  z

In [6]:

    

print(df_str.dtypes)


    

    




a    object
b    object
c    object
d    object
dtype: object

In [7]:

    

print(df_str.applymap(type))


    

    




                   a              b                c              d
ONE    <class 'str'>  <class 'str'>    <class 'str'>  <class 'str'>
TWO    <class 'str'>  <class 'str'>  <class 'float'>  <class 'str'>
THREE  <class 'str'>  <class 'str'>    <class 'str'>  <class 'str'>

In [8]:

    

df_object = pd.read_csv('data/src/sample_header_index_dtype.csv',
                        index_col=0, dtype=object)
print(df_object)


    

    




       a    b    c  d
ONE    1  001  100  x
TWO    2  020  NaN  y
THREE  3  300  300  z

In [9]:

    

print(df_object.dtypes)


    

    




a    object
b    object
c    object
d    object
dtype: object

In [10]:

    

print(df_object.applymap(type))


    

    




                   a              b                c              d
ONE    <class 'str'>  <class 'str'>    <class 'str'>  <class 'str'>
TWO    <class 'str'>  <class 'str'>  <class 'float'>  <class 'str'>
THREE  <class 'str'>  <class 'str'>    <class 'str'>  <class 'str'>

In [11]:

    

print(df.astype(str).applymap(type))


    

    




                   a              b              c              d
ONE    <class 'str'>  <class 'str'>  <class 'str'>  <class 'str'>
TWO    <class 'str'>  <class 'str'>  <class 'str'>  <class 'str'>
THREE  <class 'str'>  <class 'str'>  <class 'str'>  <class 'str'>

In [12]:

    

df_col = pd.read_csv('data/src/sample_header_index_dtype.csv',
                     index_col=0, dtype={'a': float, 'b': str})
print(df_col)


    

    




         a    b      c  d
ONE    1.0  001  100.0  x
TWO    2.0  020    NaN  y
THREE  3.0  300  300.0  z

In [13]:

    

print(df_col.dtypes)


    

    




a    float64
b     object
c    float64
d     object
dtype: object

In [14]:

    

df_col = pd.read_csv('data/src/sample_header_index_dtype.csv',
                     index_col=0, dtype={1: float, 2: str})
print(df_col)


    

    




         a    b      c  d
ONE    1.0  001  100.0  x
TWO    2.0  020    NaN  y
THREE  3.0  300  300.0  z

In [15]:

    

print(df_col.dtypes)


    

    




a    float64
b     object
c    float64
d     object
dtype: object