Get your data here. The data is related with direct marketing campaigns of a Portuguese banking institution. The marketing campaigns were based on phone calls. Often, more than one contact to the same client was required, in order to access if the product (bank term deposit) would be ('yes') or not ('no') subscribed. There are four datasets:
1) bank-additional-full.csv with all examples (41188) and 20 inputs, ordered by date (from May 2008 to November 2010)
2) bank-additional.csv with 10% of the examples (4119), randomly selected from 1), and 20 inputs.
3) bank-full.csv with all examples and 17 inputs, ordered by date (older version of this dataset with less inputs).
4) bank.csv with 10% of the examples and 17 inputs, randomly selected from 3 (older version of this dataset with less inputs).
The smallest datasets are provided to test more computationally demanding machine learning algorithms (e.g., SVM).
The classification goal is to predict if the client will subscribe (yes/no) a term deposit (variable y).
LabelEncoder useful)
In [29]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from IPython.display import Image
# This enables inline Plots
%matplotlib inline
# the pd.read... etc pulls in data using pandas to create a data frame
# set the delimiter=';'
bank_additional_full = pd.read_csv('../data/bank-additional-full.csv',header=0,index_col=False, delimiter=';')
bank_additional = pd.read_csv('../data/bank-additional.csv',header=0,index_col=False, delimiter=';')
bank_full = pd.read_csv('../data/bank-full.csv',header=0,index_col=False, delimiter=';')
bank = pd.read_csv('../data/bank.csv',header=0,index_col=False, delimiter=';')
In [33]:
bank_additional_full.head(5)
Out[33]:
In [34]:
bank_additional_full.head(5)
Out[34]:
In [35]:
bank_additional.head(5)
Out[35]:
In [36]:
bank_full.head(5)
Out[36]:
In [37]:
bank.head(5)
Out[37]:
In [40]:
# bank_additional_full.describe()
# bank_additional.describe()
# bank_full.describe()
# bank.describe()
bank_additional_full.info()
bank_additional.info()
bank_full.info()
bank.info()
In [53]:
from sklearn.datasets import load_svmlight_file
from sklearn import datasets
from sklearn import preprocessing
from sklearn.preprocessing import LabelEncoder
In [54]:
# X_train, y_train = load_svmlight_file('../data/bank-additional-full.csv',index_col=False, delimiter=';')
In [57]:
datasets.get_data_home()
Out[57]:
In [60]:
# for col in df:
# data[col] =
In [68]:
le = preprocessing.LabelEncoder()
le.fit(list(bank_additional_full.columns.values))
list(le.classes_)
label_cols = le.transform(le.classes_)
label_cols
# for col in df:
# data[col] =
Out[68]:
In [69]:
bank_full.columns
Out[69]:
In [70]:
bank_full.info()
In [129]:
numeric_cols = []
label_cols = []
for col in bank_full.columns:
if bank_full[col].dtype == 'object':
label_cols.append(col)
else:
numeric_cols.append(col)
In [131]:
bank_full.info()
In [134]:
new_DF = bank_full
label = 'string'
for i in range(len(label_cols)):
label = label_cols[i]
le.fit(list(new_DF[label].values))
list(le.classes_)
numeric_col = le.transform(le.classes_)
# for q in range(len(new_DF)):
# temp_val = le.inverse_transform(numeric_col[q])
# print new_DF[label]
# new_DF[label][q] = le.transform(q)
# le = preprocessing.LabelEncoder()
# le.fit(list(bank_full.columns.values))
# list(le.classes_)
# label_col = le.transform(le.classes_)
# label_col
In [133]:
bank_full['age'].values
Out[133]:
In [ ]:
In [97]:
for i in range(len(label_cols)):
print label_cols[i]
# label_cols[3]
In [ ]: