Python 根据列的值将列转换为多列

在Python中，我想知道是否有一种方法可以从以下内容转换一列数据帧：

为此：

源DF:

In [204]: df
Out[204]:
     Country
0      Italy
1  Indonesia
2     Canada
3      Italy

我们可以使用：

或：

---

两个附加选项

pd.Series.str.get\u假人

df.Country.str.get_dummies()

   Canada  Indonesia  Italy
0       0          0      1
1       0          1      0
2       1          0      0
3       0          0      1

df.groupby(level=0).Country.value_counts().unstack(fill_value=0)

Country  Canada  Indonesia  Italy
0             0          0      1
1             0          1      0
2             1          0      0
3             0          0      1

f, u = pd.factorize(df.Country.values)

pd.DataFrame(
    np.bincount(
        f + np.arange(f.size) * u.size, minlength=u.size * f.size
    ).reshape(f.size, u.size),
    df.index, u
)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

f, u = pd.factorize(df.Country.values)
pd.DataFrame(np.eye(u.size, dtype=int)[f], df.index, u)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

f, u = pd.factorize(df.Country.values)
a = np.zeros((f.size, u.size), dtype=int)
a[np.arange(f.size), f] = 1
pd.DataFrame(a, df.index, u)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

---

pd.DataFrame.groupby

带有

值\u计数

df.Country.str.get_dummies()

   Canada  Indonesia  Italy
0       0          0      1
1       0          1      0
2       1          0      0
3       0          0      1

df.groupby(level=0).Country.value_counts().unstack(fill_value=0)

Country  Canada  Indonesia  Italy
0             0          0      1
1             0          1      0
2             1          0      0
3             0          0      1

f, u = pd.factorize(df.Country.values)

pd.DataFrame(
    np.bincount(
        f + np.arange(f.size) * u.size, minlength=u.size * f.size
    ).reshape(f.size, u.size),
    df.index, u
)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

f, u = pd.factorize(df.Country.values)
pd.DataFrame(np.eye(u.size, dtype=int)[f], df.index, u)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

f, u = pd.factorize(df.Country.values)
a = np.zeros((f.size, u.size), dtype=int)
a[np.arange(f.size), f] = 1
pd.DataFrame(a, df.index, u)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

---

pd.factorize

+

np.bincount

df.Country.str.get_dummies()

   Canada  Indonesia  Italy
0       0          0      1
1       0          1      0
2       1          0      0
3       0          0      1

df.groupby(level=0).Country.value_counts().unstack(fill_value=0)

Country  Canada  Indonesia  Italy
0             0          0      1
1             0          1      0
2             1          0      0
3             0          0      1

f, u = pd.factorize(df.Country.values)

pd.DataFrame(
    np.bincount(
        f + np.arange(f.size) * u.size, minlength=u.size * f.size
    ).reshape(f.size, u.size),
    df.index, u
)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

f, u = pd.factorize(df.Country.values)
pd.DataFrame(np.eye(u.size, dtype=int)[f], df.index, u)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

f, u = pd.factorize(df.Country.values)
a = np.zeros((f.size, u.size), dtype=int)
a[np.arange(f.size), f] = 1
pd.DataFrame(a, df.index, u)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

---

pd.factorize

+

np.eye

df.Country.str.get_dummies()

   Canada  Indonesia  Italy
0       0          0      1
1       0          1      0
2       1          0      0
3       0          0      1

df.groupby(level=0).Country.value_counts().unstack(fill_value=0)

Country  Canada  Indonesia  Italy
0             0          0      1
1             0          1      0
2             1          0      0
3             0          0      1

f, u = pd.factorize(df.Country.values)

pd.DataFrame(
    np.bincount(
        f + np.arange(f.size) * u.size, minlength=u.size * f.size
    ).reshape(f.size, u.size),
    df.index, u
)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

f, u = pd.factorize(df.Country.values)
pd.DataFrame(np.eye(u.size, dtype=int)[f], df.index, u)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

f, u = pd.factorize(df.Country.values)
a = np.zeros((f.size, u.size), dtype=int)
a[np.arange(f.size), f] = 1
pd.DataFrame(a, df.index, u)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

---

pd.factorize

+数组片分配

df.Country.str.get_dummies()

   Canada  Indonesia  Italy
0       0          0      1
1       0          1      0
2       1          0      0
3       0          0      1

df.groupby(level=0).Country.value_counts().unstack(fill_value=0)

Country  Canada  Indonesia  Italy
0             0          0      1
1             0          1      0
2             1          0      0
3             0          0      1

f, u = pd.factorize(df.Country.values)

pd.DataFrame(
    np.bincount(
        f + np.arange(f.size) * u.size, minlength=u.size * f.size
    ).reshape(f.size, u.size),
    df.index, u
)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

f, u = pd.factorize(df.Country.values)
pd.DataFrame(np.eye(u.size, dtype=int)[f], df.index, u)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0

f, u = pd.factorize(df.Country.values)
a = np.zeros((f.size, u.size), dtype=int)
a[np.arange(f.size), f] = 1
pd.DataFrame(a, df.index, u)

   Italy  Indonesia  Canada
0      1          0       0
1      0          1       0
2      0          0       1
3      1          0       0