def main():
# df = data.read_visited_key_points('Fri', grouped=True, extra=['category'])
# categories = ['Thrill Rides', 'Kiddie Rides', 'Rides for Everyone', 'Shows & Entertainment', 'Shopping']
# df = df[df['category'].isin(categories)].sort_values('Timestamp')
#
# prev = df[df['Timestamp'] <= '2014-06-06 12'].groupby('group_id').last()
# next = df[df['Timestamp'] > '2014-06-06 12'].groupby('group_id').first()
categories = ['Thrill Rides', 'Kiddie Rides', 'Rides for Everyone', 'Shows & Entertainment', 'Shopping']
x, y, prev, ids = pp.get_bag_data(['Fri'], 11, categories, return_prev=True, return_ids=True)
# discard the day data because we only have 1 day
ids = ids['group_id'].values
# clamp x values to 1 or 0
x = (x > 0).astype('int64')
x_train, x_test, y_train, y_test, prev_train, prev_test, ids_train, ids_test = (
cross_validation.train_test_split(x, y, prev, ids, train_size=0.25, random_state=2294967295)
)
print('Predicting')
predictor = ensemble.RandomForestClassifier(n_estimators=100, max_depth=2, random_state=0)
predictor.fit(x_train, y_train)
y_pred = predictor.predict(x_test)
print('Plotting')
fig1, ax1 = plt.subplots()
fig2, ax2 = plt.subplots()
axs = [ax1, ax2]
sizes = [get_max_move_size(prev_test, y, ids_test) for y in [y_test, y_pred]]
max_size = max(sizes)
axs[0].set_title('Actual Data')
plot_next_place(prev_test, y_test, ids_test, ax=axs[0])
axs[1].set_title('Predicted')
plot_next_place(prev_test, y_pred, ids_test, ax=axs[1])
fig1.savefig('actual.png', tight=True)
fig2.savefig('predicted.png', tight=True)
plt.show()
import matplotlib
matplotlib.use('Qt4Agg')
import data
import pandas as pd
import matplotlib.pyplot as plt
import script.predict.preprocess as pp
import script.predict.predictors as pdt
from sklearn.cross_validation import train_test_split
training_size = 0.25
x, y = pp.get_bag_data(['Sat'], 12, pp.common_categories)
x_train, x_test, y_train, y_test = train_test_split(x, y, train_size=training_size, random_state=2294967295)
im = data.read_image(size=1000)
for predictor_name in pdt.all_predictors:
predictor = pdt.all_predictors[predictor_name]
predictor.fit(x_train, y_train)
y_pred = predictor.predict(x_test)
y_pred_probs = predictor.predict_proba(x_test)
kp = data.read_key_points().set_index('place_id')
# Adjust the size of this so that it's proportional to the testing data
kp['Training Counts'] = ((1 - training_size) / training_size) * pd.Series(y_train).value_counts()
kp['Test Counts'] = pd.Series(y_test).value_counts()
kp['Prediction Counts'] = pd.Series(y_pred).value_counts()
kp['Prediction Probability Sum'] = pd.DataFrame(y_pred_probs, columns=predictor.classes_).sum()
kp.fillna(0, inplace=True)
# fig, axs = plt.subplots(2, 2)
fig, axs = plt.subplots(1, 3)
fig.suptitle(predictor_name)
def main():
# df = data.read_visited_key_points('Fri', grouped=True, extra=['category'])
# categories = ['Thrill Rides', 'Kiddie Rides', 'Rides for Everyone', 'Shows & Entertainment', 'Shopping']
# df = df[df['category'].isin(categories)].sort_values('Timestamp')
#
# prev = df[df['Timestamp'] <= '2014-06-06 12'].groupby('group_id').last()
# next = df[df['Timestamp'] > '2014-06-06 12'].groupby('group_id').first()
categories = ['Thrill Rides', 'Kiddie Rides', 'Rides for Everyone', 'Shows & Entertainment', 'Shopping']
x, y, prev, ids = pp.get_bag_data(['Fri'], 14, categories, return_prev=True, return_ids=True)
# discard the day data because we only have 1 day
ids = ids['group_id'].values
# clamp x values to 1 or 0
x = (x > 0).astype('int64')
x_train, x_test, y_train, y_test, prev_train, prev_test, ids_train, ids_test = (
cross_validation.train_test_split(x, y, prev, ids, train_size=0.25, random_state=2294967295)
)
print('Predicting')
all_predictors = {
# 'Decision Tree':
# tree.DecisionTreeClassifier(),
# 'Gradient Boosting':
# ensemble.GradientBoostingClassifier(n_estimators=33, learning_rate=1.0, random_state=0),
'Random Forest':
ensemble.RandomForestClassifier(max_depth=2),
'Adaboost':
ensemble.AdaBoostClassifier(random_state=0),
'MultinomialNB':
naive_bayes.MultinomialNB(),
# 'GaussianNB': gnb_predict,
'BernoulliNB':
naive_bayes.BernoulliNB(),
# 'KNN':
# neighbors.KNeighborsClassifier(n_neighbors=10),
# 'Random':
# dummy.DummyClassifier(strategy='stratified'),
'Most Frequent':
dummy.DummyClassifier(strategy='most_frequent'),
'Uniform':
dummy.DummyClassifier(strategy='uniform'),
}
# predictor = ensemble.RandomForestClassifier(n_estimators=100, max_depth=2, random_state=0)
# predictor = ensemble.AdaBoostClassifier(random_state=0)
# predictor = naive_bayes.MultinomialNB()
# predictor = naive_bayes.BernoulliNB()
# predictor = dummy.DummyClassifier(strategy='most_frequent')
predictor = neighbors.KNeighborsClassifier(n_neighbors=10)
predictor.fit(x_train, y_train)
y_pred = predictor.predict(x_test)
print('Plotting')
fig1, ax1 = plt.subplots()
fig2, ax2 = plt.subplots()
axs = [ax1, ax2]
sizes = [get_max_move_size(prev_test, y, ids_test) for y in [y_test, y_pred]]
max_size = max(sizes)
axs[0].set_title('Actual Data')
plot_next_place(prev_test, y_test, ids_test, ax=axs[0])
axs[1].set_title('RF Predicted')
plot_next_place(prev_test, y_pred, ids_test, ax=axs[1])
# fig1.savefig('actual.png', tight=True)
# fig2.savefig('RF predicted.png', tight=True)
plt.show()
dummy.DummyClassifier(strategy='stratified'),
'Most Frequent':
dummy.DummyClassifier(strategy='most_frequent'),
'Uniform':
dummy.DummyClassifier(strategy='uniform'),
'RNN':
RNNclassifier,
# 'DNN':
# DNNclassifier
}
categories = [
'Thrill Rides', 'Kiddie Rides', 'Rides for Everyone',
'Shows and Entertainment', 'Shopping'
]
x, y = pp.get_bag_data(['Sat'], 16, categories=categories)
x = (x > 0).astype('int64')
kp = data.read_key_points().set_index('place_id')
kp = kp[kp['category'].isin(categories)]
kp['category'] = kp['category'].astype('category')
y = kp.loc[y, 'category'].cat.codes.values
x_train, x_validate, y_train, y_validate = cross_validation.train_test_split(
x, y, train_size=0.90, random_state=294967295)
# y_train_cats = kp.loc[y_train, 'category'].cat.codes.values
scorings = ['accuracy', 'log_loss']
names = []
scores = {}
def main():
# df = data.read_visited_key_points('Fri', grouped=True, extra=['category'])
# categories = ['Thrill Rides', 'Kiddie Rides', 'Rides for Everyone', 'Shows & Entertainment', 'Shopping']
# df = df[df['category'].isin(categories)].sort_values('Timestamp')
#
# prev = df[df['Timestamp'] <= '2014-06-06 12'].groupby('group_id').last()
# next = df[df['Timestamp'] > '2014-06-06 12'].groupby('group_id').first()
categories = [
'Thrill Rides', 'Kiddie Rides', 'Rides for Everyone',
'Shows & Entertainment', 'Shopping'
]
x, y, prev, ids = pp.get_bag_data(['Fri'],
14,
categories,
return_prev=True,
return_ids=True)
# discard the day data because we only have 1 day
ids = ids['group_id'].values
# clamp x values to 1 or 0
x = (x > 0).astype('int64')
x_train, x_test, y_train, y_test, prev_train, prev_test, ids_train, ids_test = (
cross_validation.train_test_split(x,
y,
prev,
ids,
train_size=0.25,
random_state=2294967295))
print('Predicting')
all_predictors = {
# 'Decision Tree':
# tree.DecisionTreeClassifier(),
# 'Gradient Boosting':
# ensemble.GradientBoostingClassifier(n_estimators=33, learning_rate=1.0, random_state=0),
'Random Forest': ensemble.RandomForestClassifier(max_depth=2),
'Adaboost': ensemble.AdaBoostClassifier(random_state=0),
'MultinomialNB': naive_bayes.MultinomialNB(),
# 'GaussianNB': gnb_predict,
'BernoulliNB': naive_bayes.BernoulliNB(),
# 'KNN':
# neighbors.KNeighborsClassifier(n_neighbors=10),
# 'Random':
# dummy.DummyClassifier(strategy='stratified'),
'Most Frequent': dummy.DummyClassifier(strategy='most_frequent'),
'Uniform': dummy.DummyClassifier(strategy='uniform'),
}
# predictor = ensemble.RandomForestClassifier(n_estimators=100, max_depth=2, random_state=0)
# predictor = ensemble.AdaBoostClassifier(random_state=0)
# predictor = naive_bayes.MultinomialNB()
# predictor = naive_bayes.BernoulliNB()
# predictor = dummy.DummyClassifier(strategy='most_frequent')
predictor = neighbors.KNeighborsClassifier(n_neighbors=10)
predictor.fit(x_train, y_train)
y_pred = predictor.predict(x_test)
print('Plotting')
fig1, ax1 = plt.subplots()
fig2, ax2 = plt.subplots()
axs = [ax1, ax2]
sizes = [
get_max_move_size(prev_test, y, ids_test) for y in [y_test, y_pred]
]
max_size = max(sizes)
axs[0].set_title('Actual Data')
plot_next_place(prev_test, y_test, ids_test, ax=axs[0])
axs[1].set_title('RF Predicted')
plot_next_place(prev_test, y_pred, ids_test, ax=axs[1])
# fig1.savefig('actual.png', tight=True)
# fig2.savefig('RF predicted.png', tight=True)
plt.show()
def main():
# df = data.read_visited_key_points('Fri', grouped=True, extra=['category'])
# categories = ['Thrill Rides', 'Kiddie Rides', 'Rides for Everyone', 'Shows & Entertainment', 'Shopping']
# df = df[df['category'].isin(categories)].sort_values('Timestamp')
#
# prev = df[df['Timestamp'] <= '2014-06-06 12'].groupby('group_id').last()
# next = df[df['Timestamp'] > '2014-06-06 12'].groupby('group_id').first()
categories = [
'Thrill Rides', 'Kiddie Rides', 'Rides for Everyone',
'Shows & Entertainment', 'Shopping'
]
x, y, prev, ids = pp.get_bag_data(['Fri'],
14,
categories,
return_prev=True,
return_ids=True)
# discard the day data because we only have 1 day
ids = ids['group_id'].values
# clamp x values to 1 or 0
x = (x > 0).astype('int64')
x_train, x_test, y_train, y_test, prev_train, prev_test, ids_train, ids_test = (
cross_validation.train_test_split(x,
y,
prev,
ids,
train_size=0.25,
random_state=2294967295))
print('Predicting')
#################################random forest##################################
predictor = ensemble.RandomForestClassifier(n_estimators=100,
max_depth=2,
random_state=0)
predictor.fit(x_train, y_train)
y_pred1 = predictor.predict(x_test)
################################RNN##################################
# Build model: a single direction GRU with a single layer
classifier = learn.TensorFlowRNNClassifier(rnn_size=EMBEDDING_SIZE,
n_classes=82,
cell_type='gru',
input_op_fn=input_op_fn,
num_layers=1,
bidirectional=False,
sequence_length=None,
steps=1000,
optimizer='Adam',
learning_rate=0.01,
continue_training=True)
# print(x_train)
# print(y_train)
# Train and predict
classifier.fit(x_train, y_train, steps=1000)
y_pred2 = classifier.predict(x_test)
print('Plotting')
fig1, ax1 = plt.subplots()
fig2, ax2 = plt.subplots()
fig3, ax3 = plt.subplots()
axs = [ax1, ax2, ax3]
# sizes = [get_max_move_size(prev_test, y, ids_test) for y in [y_test, y_pred]]
# max_size = max(sizes)
axs[0].set_title('Actual Data')
plot_next_place(prev_test, y_test, ids_test, ax=axs[0])
axs[1].set_title('RNN Predicted')
plot_next_place(prev_test, y_pred2, ids_test, ax=axs[1])
axs[2].set_title('RF Predicted')
plot_next_place(prev_test, y_pred1, ids_test, ax=axs[2])
fig1.savefig('actual.png', tight=True)
fig2.savefig('RNN predicted.png', tight=True)
plt.show()