#!/usr/bin/env python
# coding: utf-8

# In[1]:


import pandas as pd
import numpy as np
import skflow as sf
import tensorflow as tf
from sklearn.cross_validation import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score


# In[2]:


np.random.seed(42)


# In[3]:


data = pd.read_csv('tf_examples/data/titanic_train.csv')
data.head()


# In[4]:


predictors = ['Age', 'SibSp', 'Fare', 'Parch', 'Pclass', 'Sex']


# In[5]:


X_train, X_test, y_train, y_test = train_test_split(data[predictors].replace({'Sex':{'male':0, 
                                                                                     'female':1}}).fillna(data.mean()), 
                                                    data.Survived)


# In[6]:


lr = LogisticRegression()
lr.fit(X_train, y_train)
lr.score(X_test, y_test)


# In[7]:


classifier = sf.TensorFlowLinearClassifier(n_classes=2, 
                                           batch_size=128, 
                                           steps=500, 
                                           learning_rate=0.05)


# In[8]:


classifier.fit(X_train, y_train)


# In[9]:


classifier.score(X_test, y_test)


# In[10]:


classifier = sf.TensorFlowDNNClassifier(
     hidden_units=[10, 20, 20, 10], 
     n_classes=2, 
     batch_size=128, 
     steps=20000, 
     learning_rate=0.05)


# In[11]:


classifier.fit(X_train, y_train)


# In[12]:


classifier.score(X_test, y_test)


# In[13]:


from tensorflow import tanh

def dnn_tanh(X, y):
    layers = sf.ops.dnn(X, [10, 20, 10], tanh)
    return sf.models.logistic_regression(layers, y)

classifier = sf.TensorFlowEstimator(
    model_fn=dnn_tanh, 
    n_classes=2,
    batch_size=128,
    steps=500,
    learning_rate=0.05)


# In[14]:


classifier.fit(X_train, y_train)


# In[15]:


score = accuracy_score(classifier.predict(X_test), y_test)
score


# ## Digit recognition

# In[16]:


from sklearn import datasets
digits = datasets.load_digits()


# In[17]:


X = digits.images
y = digits.target

X_train, X_test, y_train, y_test = train_test_split(X, y,
    test_size=0.2, random_state=42)


# This function creates a 2-dimensional convolutional layer with max pooling.

# In[18]:


def conv_model(X, y):
    X = tf.expand_dims(X, 3)
    features = tf.reduce_max(sf.ops.conv2d(X, 12, [3, 3]), [1, 2])
    features = tf.reshape(features, [-1, 12])
    return sf.models.logistic_regression(features, y)


# In[19]:


classifier = sf.TensorFlowEstimator(model_fn=conv_model, n_classes=10,
                                        steps=5000, learning_rate=0.05,
                                        batch_size=128)
classifier.fit(X_train, y_train)


# In[20]:


score = accuracy_score(classifier.predict(X_test), y_test)
score