ファセットと相互作用項を使用した TensorFlow 線形回帰

!conda install -- yes matplotlib

import sys
!{sys.executable} -m pip install matplotlib # Already installed
!{sys.executable} -m pip install seaborn 

import pandas as pd
from sklearn import datasets
import tensorflow as tf
from sklearn.datasets import load_boston
import numpy as np

boston = load_boston()
df = pd.DataFrame(boston.data)

boston.feature_names

array(['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD','TAX', 'PTRATIO', 'B', 'LSTAT'], dtype='<U7')

df.columns = boston.feature_names
df['PRICE'] = boston.target
df.head(2)

df['CHAS'] = df['CHAS'].map({1:'yes', 0:'no'})
df['CHAS'].head(5)
0    no
1    no
2    no
3    no
4    no
Name: CHAS, dtype: object

### Create train/test set
df_train=df.sample(frac=0.8,random_state=200)
df_test=df.drop(df_train.index)

print(df_train.shape, df_test.shape)

(405, 14) (101, 14)

df_test.head(5)

pip install jupyter_contrib_nbextensions

git clone https://github.com/PAIR-code/facets

echo `pwd`/`ls facets`

cd facets

jupyter nbextension install facets-dist/

jupyter nbextension install facets-dist/ --user

# Add the facets overview python code to the python path# Add t 
import sys
sys.path.append('/Users/Thomas/facets/facets_overview/python')

from generic_feature_statistics_generator import 
GenericFeatureStatisticsGenerator

import sys
sys.path.append(r"C:\Users\Admin\Anaconda3\facets-master\facets_overview\python")

from generic_feature_statistics_generator import GenericFeatureStatisticsGenerator

'name': 'train', 'table': df_train

# Calculate the feature statistics proto from the datasets and stringify it for use in facets overview
import base64

gfsg = GenericFeatureStatisticsGenerator()

proto = gfsg.ProtoFromDataFrames([{'name': 'train', 'table': df_train},
                                  {'name': 'test', 'table': df_test}])

#proto = gfsg.ProtoFromDataFrames([{'name': 'train', 'table': df_train}])
protostr = base64.b64encode(proto.SerializeToString()).decode("utf-8")

# Display the facets overview visualization for this data# Displ 
from IPython.core.display import display, HTML

HTML_TEMPLATE = """<link rel="import" href="/nbextensions/facets-dist/facets-jupyter.html" >
        <facets-overview id="elem"></facets-overview>
        <script>
          document.querySelector("#elem").protoInput = "{protostr}";
        </script>"""
html = HTML_TEMPLATE.format(protostr=protostr)
display(HTML(html))

## Choose important feature and further check with Dive
%matplotlib inline  
import matplotlib.pyplot as plt
import seaborn as sns
sns.set(style="ticks")
# Compute the correlation matrix
corr = df.corr('pearson')
# Generate a mask for the upper triangle
mask = np.zeros_like(corr, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True
# Set up the matplotlib figure
f, ax = plt.subplots(figsize=(11, 9))

# Generate a custom diverging colormap
cmap = sns.diverging_palette(220, 10, as_cmap=True)

# Draw the heatmap with the mask and correct aspect ratio
sns.heatmap(corr, mask=mask, cmap=cmap, vmax=.3, center=0,annot=True,
            square=True, linewidths=.5, cbar_kws={"shrink": .5})

<matplotlib.axes._subplots.AxesSubplot at 0x1a184d6518>

attributes = ["PRICE", "INDUS", "NOX", "RM", "LSTAT"]

g = sns.PairGrid(df[attributes])
g = g.map_upper(sns.regplot, color="g")
g = g.map_lower(sns.kdeplot,cmap="Reds", shade=True, shade_lowest=False)
g = g.map_diag(sns.kdeplot)

## Check non linearity with important features
df['Q_PRICE'] =  pd.qcut(df['PRICE'], 4, labels=["Lowest", "Low", "Upper", "upper_plus"])
## Show non linearity between RM and LSTAT
ax = sns.lmplot(x="DIS", y="INDUS", hue="Q_PRICE", data=df, fit_reg = False,palette="Set3")

df['Q_PRICE'] =  pd.qcut(df['PRICE'], 4, labels=["Lowest", "Low", "Upper", "upper_plus"])
sprite_size = 32 if len(df.index)>50000 else 64
jsonstr = df.to_json(orient='records')

# Display thde Dive visualization for this data
from IPython.core.display import display, HTML

# Create Facets template  
HTML_TEMPLATE = """<link rel="import" href="/nbextensions/facets-dist/facets-jupyter.html">
        <facets-dive sprite-image-width="{sprite_size}" sprite-image-height="{sprite_size}" id="elem" height="600"></facets-dive>
        <script>
          document.querySelector("#elem").data = {jsonstr};
        </script>"""

# Load the json dataset and the sprite_size into the template
html = HTML_TEMPLATE.format(jsonstr=jsonstr, sprite_size=sprite_size)

# Display the template
display(HTML(html))

from sklearn import preprocessing
def standardize_data(df): 
    X_scaled = preprocessing.scale(df[['CRIM', 'ZN', 'INDUS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD',
       'TAX', 'PTRATIO', 'B', 'LSTAT']])
    X_scaled_df = pd.DataFrame(X_scaled, columns = ['CRIM', 'ZN', 'INDUS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD',
       'TAX', 'PTRATIO', 'B', 'LSTAT'])
    df_scale = pd.concat([X_scaled_df,
                       df['CHAS'],
                       df['PRICE']],axis=1, join='inner')
    return df_scale

df_train_scale = standardize_data(df_train)
df_test_scale = standardize_data(df_test)

## Add features to the bucket: 
### Define continuous list
CONTI_FEATURES  = ['CRIM', 'ZN', 'INDUS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD','TAX', 'PTRATIO', 'B', 'LSTAT']
CATE_FEATURES = ['CHAS']

continuous_features = [tf.feature_column.numeric_column(k) for k in CONTI_FEATURES]
#categorical_features = tf.feature_column.categorical_column_with_hash_bucket(CATE_FEATURES, hash_bucket_size=1000)
categorical_features = [tf.feature_column.categorical_column_with_vocabulary_list('CHAS', ['yes','no'])]

model = tf.estimator.LinearRegressor(    
	model_dir="train_Boston",     
    feature_columns=categorical_features + continuous_features)

INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_model_dir': 'train_Boston', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': None, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x1a19e76ac8>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}

FEATURES = ['CRIM', 'ZN', 'INDUS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD','TAX', 'PTRATIO', 'B', 'LSTAT', 'CHAS']
LABEL= 'PRICE'
def get_input_fn(data_set, num_epochs=None, n_batch = 128, shuffle=True):
    return tf.estimator.inputs.pandas_input_fn(
       x=pd.DataFrame({k: data_set[k].values for k in FEATURES}),
       y = pd.Series(data_set[LABEL].values),
       batch_size=n_batch,   
       num_epochs=num_epochs,
       shuffle=shuffle)

model.train(input_fn=get_input_fn(df_train_scale, 
                                      num_epochs=None,
                                      n_batch = 128,
                                      shuffle=False),
                                      steps=1000)

INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Saving checkpoints for 1 into train_Boston/model.ckpt.
INFO:tensorflow:loss = 56417.703, step = 1
INFO:tensorflow:global_step/sec: 144.457
INFO:tensorflow:loss = 76982.734, step = 101 (0.697 sec)
INFO:tensorflow:global_step/sec: 258.392
INFO:tensorflow:loss = 21246.334, step = 201 (0.383 sec)
INFO:tensorflow:global_step/sec: 227.998
INFO:tensorflow:loss = 30534.78, step = 301 (0.439 sec)
INFO:tensorflow:global_step/sec: 210.739
INFO:tensorflow:loss = 36794.5, step = 401 (0.477 sec)
INFO:tensorflow:global_step/sec: 234.237
INFO:tensorflow:loss = 8562.981, step = 501 (0.425 sec)
INFO:tensorflow:global_step/sec: 238.1
INFO:tensorflow:loss = 34465.08, step = 601 (0.420 sec)
INFO:tensorflow:global_step/sec: 237.934
INFO:tensorflow:loss = 12241.709, step = 701 (0.420 sec)
INFO:tensorflow:global_step/sec: 220.687
INFO:tensorflow:loss = 11019.228, step = 801 (0.453 sec)
INFO:tensorflow:global_step/sec: 232.702
INFO:tensorflow:loss = 24049.678, step = 901 (0.432 sec)
INFO:tensorflow:Saving checkpoints for 1000 into train_Boston/model.ckpt.
INFO:tensorflow:Loss for final step: 23228.568.


<tensorflow.python.estimator.canned.linear.LinearRegressor at 0x1a19e76320>

model.evaluate(input_fn=get_input_fn(df_test_scale, 
                                      num_epochs=1,
                                      n_batch = 128,
                                      shuffle=False),
                                      steps=1000)

INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Starting evaluation at 2018-05-29-02:40:43
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Restoring parameters from train_Boston/model.ckpt-1000
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Finished evaluation at 2018-05-29-02:40:43
INFO:tensorflow:Saving dict for global step 1000: average_loss = 86.89361, global_step = 1000, loss = 1650.9785


{'average_loss': 86.89361, 'global_step': 1000, 'loss': 1650.9785}

def interaction_term(var_1, var_2, name):
    t_train = df_train_scale[var_1]*df_train_scale[var_2]
    train = t_train.rename(name)
    t_test = df_test_scale[var_1]*df_test_scale[var_2]
    test = t_test.rename(name)
    return train, test

interation_ind_ns_train, interation_ind_ns_test= interaction_term('INDUS', 'NOX', 'INDUS_NOS')
interation_ind_ns_train.shape
(325,)

def triple_interaction_term(var_1, var_2,var_3, name):
    t_train = df_train_scale[var_1]*df_train_scale[var_2]*df_train_scale[var_3]
    train = t_train.rename(name)
    t_test = df_test_scale[var_1]*df_test_scale[var_2]*df_test_scale[var_3]
    test = t_test.rename(name)
    return train, test
interation_ind_ns_dis_train, interation_ind_ns_dis_test= triple_interaction_term('INDUS', 'NOX', 'DIS','INDUS_NOS_DIS')

df_train_new = pd.concat([df_train_scale,
                          interation_ind_ns_train,
                          interation_ind_ns_dis_train],
                         axis=1, join='inner')
df_test_new = pd.concat([df_test_scale,
                         interation_ind_ns_test,
                         interation_ind_ns_dis_test],
                         axis=1, join='inner')
df_train_new.head(5)

CONTI_FEATURES_NEW  = ['CRIM', 'ZN', 'INDUS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD','TAX', 'PTRATIO', 'B', 'LSTAT',
                       'INDUS_NOS', 'INDUS_NOS_DIS']
### Define categorical list
continuous_features_new = [tf.feature_column.numeric_column(k) for k in CONTI_FEATURES_NEW]
model = tf.estimator.LinearRegressor(
    model_dir="train_Boston_1", 
    feature_columns= categorical_features + continuous_features_new)

INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_model_dir': 'train_Boston_1', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': None, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x1a1a5d5860>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}

FEATURES = ['CRIM', 'ZN', 'INDUS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD','TAX', 'PTRATIO', 'B', 'LSTAT','INDUS_NOS', 'INDUS_NOS_DIS','CHAS']
LABEL= 'PRICE'
def get_input_fn(data_set, num_epochs=None, n_batch = 128, shuffle=True):
    return tf.estimator.inputs.pandas_input_fn(
       x=pd.DataFrame({k: data_set[k].values for k in FEATURES}),
       y = pd.Series(data_set[LABEL].values),
       batch_size=n_batch,   
       num_epochs=num_epochs,
       shuffle=shuffle)

model.train(input_fn=get_input_fn(df_train_new, 
                                      num_epochs=None,
                                      n_batch = 128,
                                      shuffle=False),
                                      steps=1000)

INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Saving checkpoints for 1 into train_Boston_1/model.ckpt.
INFO:tensorflow:loss = 56417.703, step = 1
INFO:tensorflow:global_step/sec: 124.844
INFO:tensorflow:loss = 65522.3, step = 101 (0.803 sec)
INFO:tensorflow:global_step/sec: 182.704
INFO:tensorflow:loss = 15384.148, step = 201 (0.549 sec)
INFO:tensorflow:global_step/sec: 208.189
INFO:tensorflow:loss = 22020.305, step = 301 (0.482 sec)
INFO:tensorflow:global_step/sec: 213.855
INFO:tensorflow:loss = 28208.812, step = 401 (0.468 sec)
INFO:tensorflow:global_step/sec: 209.758
INFO:tensorflow:loss = 7606.877, step = 501 (0.473 sec)
INFO:tensorflow:global_step/sec: 196.618
INFO:tensorflow:loss = 26679.76, step = 601 (0.514 sec)
INFO:tensorflow:global_step/sec: 196.472
INFO:tensorflow:loss = 11377.163, step = 701 (0.504 sec)
INFO:tensorflow:global_step/sec: 172.82
INFO:tensorflow:loss = 8592.07, step = 801 (0.578 sec)
INFO:tensorflow:global_step/sec: 168.916
INFO:tensorflow:loss = 19878.56, step = 901 (0.592 sec)
INFO:tensorflow:Saving checkpoints for 1000 into train_Boston_1/model.ckpt.
INFO:tensorflow:Loss for final step: 19598.387.


<tensorflow.python.estimator.canned.linear.LinearRegressor at 0x1a1a5d5e10>

model.evaluate(input_fn=get_input_fn(df_test_new, 
                                      num_epochs=1,
                                      n_batch = 128,
                                      shuffle=False),
                                      steps=1000)

INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Starting evaluation at 2018-05-29-02:41:14
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Restoring parameters from train_Boston_1/model.ckpt-1000
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Finished evaluation at 2018-05-29-02:41:14
INFO:tensorflow:Saving dict for global step 1000: average_loss = 79.78876, global_step = 1000, loss = 1515.9863


{'average_loss': 79.78876, 'global_step': 1000, 'loss': 1515.9863}