def findUnigrams():
unigrams = []
conditions = []
i = 0;
# iterate through each user's tweets
for fileName in os.listdir(dataPath):
i += 1
with open(dataPath + fileName, 'r+') as f:
print("Started Parsing: " + fileName)
joinedTweets = ""
for line in f:
dataPayload = json.loads(line)
condition = dataPayload['metadata']['condition']
if condition == "ptsd":
print "PTSD"
continue
userCorpus = dataPayload['allTokensLemmatized']
# removing stop words from the entire corupus
userCorpus = removeStopWords(userCorpus)
unigrams.append(" ".join(userCorpus))
if condition == "control":
conditions.append(1)
else:
conditions.append(0)
forest = RandomForestClassifier(n_estimators = 100)
# forest = forest.fit(train_data_features, train["sentiment"] )
vectorizer = CountVectorizer(analyzer = "word", \
tokenizer = None, \
preprocessor = None, \
stop_words = None, \
max_features = 5000)
train_data_features = vectorizer.fit_transform(unigrams)
train_data_features = train_data_features.toarray()
score = cvs(forest, train_data_features, conditions, cv=10)
print score
# with open('../outputs/unigrams.json', 'w') as outfile:
# json.dump(featureDict, outfile)
print 'done writing unigrams ' + str(i)
def build(args):
"""
Builds the models from the arguments.
In a real applciation, would probably arguments:
- fixtures (where the training data is)
- model_dir (where to write the models out to)
- kfolds (number of cross validation folds)
For now, just write out the pickles to HEAT_MODEL and COLD_MODEL
"""
start = time.time()
# Load data and estimator
dataset = load_energy()
alphas = np.logspace(-10, -2, 200)
scores = {}
for y in ('Y1', 'Y2'):
# Perform cross validation, don't worry about Imputation here
clf = linear_model.RidgeCV(alphas=alphas)
scores[y] = cvs(clf, dataset.data, dataset.target(y), cv=12)
# Get the alpha from the ridge by fitting the entire data set.
# There are a couple of reasons for this, but mostly to ensure that
# we get the desired result pickled (e.g. a ridge with alpha)
clf.fit(dataset.data, dataset.target(y))
# Build the model on the entire datset include Imputer pipeline
model = linear_model.Ridge(alpha=clf.alpha_)
imputer = Imputer(missing_values="NaN", strategy="mean", axis=0)
estimator = Pipeline([("imputer", imputer), ("ridge", model)])
estimator.fit(dataset.data, dataset.target(y))
# Dump the model
jump = {
'Y1': HEAT_MODEL,
'Y2': COLD_MODEL,
}
with open(jump[y], 'wb') as f:
pickle.dump(estimator, f, protocol=pickle.HIGHEST_PROTOCOL)
msg = ("%s trained on %i instances using a %s model\n"
" average R2 score of %0.3f using an alpha of %0.5f\n"
" model has been dumped to %s\n")
print(msg % (
y,
len(dataset.data),
model.__class__.__name__,
scores[y].mean(),
clf.alpha_,
jump[y],
))
build_time = time.time() - start
return "Build took %0.3f seconds" % build_time
def build(args):
"""
Builds the models from the arguments.
In a real applciation, would probably arguments:
- fixtures (where the training data is)
- model_dir (where to write the models out to)
- kfolds (number of cross validation folds)
For now, just write out the pickles to HEAT_MODEL and COLD_MODEL
"""
start = time.time()
# Load data and estimator
dataset = load_energy()
alphas = np.logspace(-10, -2, 200)
scores = {}
for y in ('Y1', 'Y2'):
# Perform cross validation, don't worry about Imputation here
clf = linear_model.RidgeCV(alphas=alphas)
scores[y] = cvs(clf, dataset.data, dataset.target(y), cv=12)
# Get the alpha from the ridge by fitting the entire data set.
# There are a couple of reasons for this, but mostly to ensure that
# we get the desired result pickled (e.g. a ridge with alpha)
clf.fit(dataset.data, dataset.target(y))
# Build the model on the entire datset include Imputer pipeline
model = linear_model.Ridge(alpha=clf.alpha_)
imputer = Imputer(missing_values="NaN", strategy="mean", axis=0)
estimator = Pipeline([("imputer", imputer), ("ridge", model)])
estimator.fit(dataset.data, dataset.target(y))
# Dump the model
jump = {
'Y1': HEAT_MODEL,
'Y2': COLD_MODEL,
}
with open(jump[y], 'wb') as f:
pickle.dump(estimator, f, protocol=pickle.HIGHEST_PROTOCOL)
msg = (
"%s trained on %i instances using a %s model\n"
" average R2 score of %0.3f using an alpha of %0.5f\n"
" model has been dumped to %s\n"
)
print(msg % (
y, len(dataset.data), model.__class__.__name__,
scores[y].mean(), clf.alpha_,
jump[y],
))
build_time = time.time() - start
return "Build took %0.3f seconds" % build_time
#KNN
knn = knc(p=2) #specify Euclidean distance
param_grid = dict(n_neighbors=range(1, 30, 2)) #set up grid for results
kn_accuracy = gscv(knn, param_grid, cv=10,
scoring='accuracy').fit(df_exp, df_res)
param_grid = dict(n_neighbors=range(1, 30, 2)) #set up grid for results
kn_f1 = gscv(knn, param_grid, cv=10, scoring='f1').fit(df_exp, df_res)
param_grid = dict(n_neighbors=range(1, 30, 2)) #set up grid for results
kn_auc = gscv(knn, param_grid, cv=10, scoring='roc_auc').fit(df_exp, df_res)
#Naive Bayes
nb = mnb()
nb_accuracy = cvs(nb, df_exp, df_res, cv=10, scoring='accuracy')
nb_f1 = cvs(nbclass, df_exp, df_res, cv=10, scoring='f1')
nb_auc = cvs(nbclass, df_exp, df_res, cv=10, scoring='roc_auc')
#Decision Tree
dtree = tr.DecisionTreeClassifier(criterion='gini',
splitter='best',
max_features=None,
max_depth=None,
min_samples_split=2,
min_samples_leaf=2,
max_leaf_nodes=None)
param_grid = dict(max_depth=range(1, 23))
dt_accuracy = gscv(dtree, param_grid, cv=10,
scoring='accuracy').fit(df_exp, df_res)
#KNN knn=knc(p = 2) #specify Euclidean distance param_grid = dict(n_neighbors=range(1,30, 2)) #set up grid for results kn_accuracy=gscv(knn, param_grid, cv=10, scoring='accuracy').fit(df_exp, df_res) param_grid = dict(n_neighbors=range(1,30, 2)) #set up grid for results kn_f1=gscv(knn, param_grid, cv=10, scoring='f1').fit(df_exp, df_res) param_grid = dict(n_neighbors=range(1,30, 2)) #set up grid for results kn_auc=gscv(knn, param_grid, cv=10, scoring='roc_auc').fit(df_exp, df_res) #Naive Bayes nb = mnb() nb_accuracy = cvs(nb, df_exp, df_res, cv=10, scoring='accuracy') nb_f1 = cvs(nbclass, df_exp, df_res, cv=10, scoring='f1') nb_auc = cvs(nbclass, df_exp, df_res, cv=10, scoring='roc_auc') #Decision Tree dtree = tr.DecisionTreeClassifier(criterion = 'gini', splitter = 'best', max_features = None, max_depth = None,min_samples_split = 2, min_samples_leaf = 2, max_leaf_nodes = None) param_grid = dict(max_depth=range(1, 23)) dt_accuracy = gscv(dtree, param_grid, cv=10, scoring='accuracy').fit(df_exp, df_res) param_grid = dict(max_depth=range(1, 23)) dt_f1 = gscv(dtree, param_grid, cv=10, scoring='f1').fit(df_exp, df_res) param_grid = dict(max_depth=range(1, 23)) dt_auc = gscv(dtree, param_grid, cv=10, scoring='roc_auc').fit(df_exp, df_res)
import SVM as CLF
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cross_validation import cross_val_score as cvs
from sklearn.ensemble import AdaBoostClassifier as ABC
df, salary, keys = CLF.clean(CLF.get_data())
estimators = [10, 20, 30, 40, 50, 100, 200, 400]
estimator_scores = []
for estimator in estimators:
clf = ABC(n_estimators=estimator)
estimator_scores.append(cvs(clf, df, salary).mean())
learning_rates = [1, 10, 20, 30, 40, 50, 100, 200]
learning_scores = []
best_estimator = estimators[estimator_scores.index(max(estimator_scores))]
for rate in learning_rates:
clf = ABC(n_estimators=best_estimator, learning_rate=rate)
learning_scores.append(cvs(clf, df, salary).mean())
n_estimators = 400
# A learning rate of 1. may not be optimal for both SAMME and SAMME.R
learning_rate = 1.
fig = plt.figure()
ax = fig.add_subplot(111)
x+= pegasos_svm_test(train_set[test], w);
y_axis.append(x/5);
print(i);
plt.title("Cross Validation Error");
plt.xlabel("Lambda");
plt.ylabel("Error");
plt.plot(x_axis,y_axis);
w = pegasos_svm_train(train_set,2**-3);
print(pegasos_svm_test(test_set,w));
### Question 2d###
clf = OneVsRestClassifier(SVC()).fit(train_set_x, train_set_y);
y = clf.predict(test_set_x);
print((test_num-np.sum(np.equal(y,test_set_y)))/test_num);
### Question 2e ###
print(1-np.mean(cvs(OneVsRestClassifier(SVC()),train_set_x,y=train_set_y,cv=10)));
### Question 2f ###
print(1-np.mean(cvs(OneVsRestClassifier(SVC()),train_set_x,y=train_set_y,cv=10)));
print(1-np.mean(cvs(OneVsRestClassifier(SVC(gamma=1/len(train_set)**2,C=100)),train_set_x,y=train_set_y,cv=10)));
print(1-np.mean(cvs(OneVsRestClassifier(SVC(gamma=1/len(train_set)**2,C=1)),train_set_x,y=train_set_y,cv=10)));
print(1-np.mean(cvs(OneVsRestClassifier(SVC(gamma=0,C=.0001)),train_set_x,y=train_set_y,cv=10)));
print(1-np.mean(cvs(OneVsRestClassifier(SVC(C=1.5)),train_set_x,y=train_set_y,cv=10)));
print(1-np.mean(cvs(OneVsRestClassifier(SVC(C=10000)),train_set_x,y=train_set_y,cv=10)));
print(1-np.mean(cvs(OneVsRestClassifier(SVC(gamma=.001, C=1)),train_set_x,y=train_set_y,cv=10)));
print(1-np.mean(cvs(OneVsRestClassifier(SVC(gamma=0.01, C=1000)),train_set_x,y=train_set_y,cv=10)));
print(1-np.mean(cvs(OneVsRestClassifier(SVC(gamma=1/len(train_set),C=100)),train_set_x,y=train_set_y,cv=10)));
bnb.fit(df_train, out_train)
bnb.score(df_test, out_test)
# ### Better, but still not close to 90%
# #### So the Naive Bayes Classifier also doesnot do a good job in this task.
# #### Now I will try and experiment with Tree based classifiers.
# ## Decision Trees
# In[ ]:
from sklearn.cross_validation import cross_val_score as cvs
from sklearn.tree import DecisionTreeClassifier as dtree
tr = dtree()
cvs(tr, df_train, out_train, cv=10)
# ### Playing around with the tree parameters
#
# #### Effect of changing the max depth
# In[ ]:
for i in range(2, 20):
tr = dtree(max_depth=i)
print("Max Depth = " + str(i) + "\t Score: ")
print(np.mean(cvs(tr, df_train, out_train, cv=10)))
print("\n")
# ### Visualization of effects of max depth