import pandas as pd
from sklearn import preprocessing
x = df.values #returns a numpy array
min_max_scaler = preprocessing.MinMaxScaler()
x_scaled = min_max_scaler.fit_transform(x)
df = pd.DataFrame(x_scaled)In [5]: %paste
cols = ['2002', '2003', '2004', '2005']
df[cols] = df[cols] / df[cols].sum()
## -- End pasted text --
In [6]: df
Out[6]:
term 2002 2003 2004 2005
0 climate 0.043478 0.454545 0.333333 0.466667
1 global 0.521739 0.500000 0.666667 0.400000
2 nuclear 0.434783 0.045455 0.000000 0.133333import pandas as pd
df = pd.DataFrame(
columns=['term', '2002', '2003', '2004', '2005'],
data=[['climate', 1, 10, 1, 14],
['global', 12, 11, 2, 12],
['nuclear', 10, 1, 0, 4], ])
normalized = df.select_dtypes('int').apply(lambda x: x / sum(x))
df = df.merge(
right=normalized,
left_index=True,
right_index=True,
suffixes=['', '_norm']
)# define a method to scale data, looping thru the columns, and passing a scaler
def scale_data(data, columns, scaler):
for col in columns:
data[col] = scaler.fit_transform(data[col].values.reshape(-1, 1))
return data