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 [8]:
# Standard imports
import pandas as pd
import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
from sklearn import preprocessing
pd.set_option('display.max_rows', 10)
In [9]:
print 'Pandas:', pd.__version__
print 'Numpy:', np.__version__
print 'Matplotlib:', mpl.__version__
In [10]:
data_addl = pd.read_csv('bank-additional-full.csv', delimiter=";")
data_addl.describe()
#data_addl.info()
data_addl.education.unique()
data_addl.month.unique()
#need to encode job, marital, education, default, housing, loan, contact, month, day_of_week, poutcome, y?
Out[10]:
In [11]:
obj_fields = ['y','job', 'marital', 'education', 'default', 'housing', 'loan', 'contact', 'month', 'day_of_week', 'poutcome']
num_fields = ['age','duration','campaign','pdays','previous','emp.var.rate','cons.price.idx','cons.conf.idx','euribor3m','nr.employed']
dataX = data_addl[num_fields]
for field in obj_fields:
print field
le = preprocessing.LabelEncoder()
le.fit(data_addl[field])
# print list(le.classes_)
data_addl[field] = le.transform(data_addl[field])
# le_field = pd.DataFrame(le_field)
# print len(le_field)
# print le_field_df.info()
# dataX.append(le_field, ignore_index=True)
# print dataX.columns
#print data_addl.head()
print data_addl.describe()
In [12]:
le_df = pd.DataFrame(lelist)
le_df = le_df.transpose()
le_df.columns = fields
In [13]:
#le_df.head()
#data_addl.info()
#num_fields = ['age','duration','campaign','pdays','previous','emp.var.rate','cons.price.idx','cons.conf.idx','euribor3m','nr.employed']
#data = le_df.merge(data_addl[num_fields], ignore_index=True)
data_fields = [col for col in data_addl.columns if col not in ['y']]
print data_fields
features = data_addl[data_fields]
features.head()
Out[13]:
In [14]:
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(features, data_addl.y, test_size=0.3)
In [15]:
from sklearn.cross_validation import cross_val_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.tree import DecisionTreeClassifier
X_train = pd.DataFrame(X_train, columns=features.columns)
In [16]:
%%time
rf_model = RandomForestClassifier(n_estimators=100,max_depth=15,criterion='entropy')
rf_model.fit(X_train, y_train)
print cross_val_score(rf_model, X_train, y_train).mean()
In [17]:
#importance
sorted(zip(rf_model.feature_importances_,features.columns),reverse=True)
#sorted(zip(rf_model.feature_importances_, vectorizer.get_feature_names()), reverse=True)[:20]
Out[17]:
In [18]:
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import confusion_matrix
neigh = KNeighborsClassifier(n_neighbors=2)
neigh.fit(X_train, y_train)
y_pred = neigh.predict(X_test)
def plot_confusion_matrix(y_pred, y):
plt.imshow(confusion_matrix(y, y_pred),
cmap=plt.cm.binary, interpolation='nearest')
plt.colorbar()
plt.xlabel('true value')
plt.ylabel('predicted value')
plot_confusion_matrix(y_pred,y_test)
In [19]:
from sklearn.metrics import classification_report
print classification_report(y_test,y_pred)
In [20]:
%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt
from sklearn.learning_curve import learning_curve
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
"""
Generate a simple plot of the test and traning learning curve.
Parameters
----------
estimator : object type that implements the "fit" and "predict" methods
An object of that type which is cloned for each validation.
title : string
Title for the chart.
X : array-like, shape (n_samples, n_features)
Training vector, where n_samples is the number of samples and
n_features is the number of features.
y : array-like, shape (n_samples) or (n_samples, n_features), optional
Target relative to X for classification or regression;
None for unsupervised learning.
ylim : tuple, shape (ymin, ymax), optional
Defines minimum and maximum yvalues plotted.
cv : integer, cross-validation generator, optional
If an integer is passed, it is the number of folds (defaults to 3).
Specific cross-validation objects can be passed, see
sklearn.cross_validation module for the list of possible objects
n_jobs : integer, optional
Number of jobs to run in parallel (default 1).
"""
plt.figure()
plt.title(title)
if ylim is not None:
plt.ylim(*ylim)
plt.xlabel("Training examples")
plt.ylabel("Score")
train_sizes, train_scores, test_scores = learning_curve(
estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
train_scores_mean = np.mean(train_scores, axis=1)
train_scores_std = np.std(train_scores, axis=1)
test_scores_mean = np.mean(test_scores, axis=1)
test_scores_std = np.std(test_scores, axis=1)
plt.grid()
plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
train_scores_mean + train_scores_std, alpha=0.1,
color="r")
plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
test_scores_mean + test_scores_std, alpha=0.1, color="g")
plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
label="Training score")
plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
label="Cross-validation score")
plt.legend(loc="best")
return plt
In [21]:
%%time
#this is an example of 1 learning curve for 1 model, try a few more.
_ = plot_learning_curve(RandomForestClassifier(n_estimators=100),'test',X_train,y_train)
In [ ]: