def parse_file(self, sgmfiles):
'''
accesses the given files and finds the
content between the required tags
'''
for filename in sgmfiles:
fopen = open(filename, 'r')
lines = fopen.read()
fopen.close()
pattern = "<REUTERS[^>]*>([\s\S]*?)</REUTERS>"
reuters = re.findall(pattern, lines)
for line in reuters:
rec_dict = {}
#removing special characters from the obtained text
line = CleanData().clean_spc_articles(line)
rec_dict['REUTERS'] = line
t_pttrn = "<TITLE>(.*?)</TITLE>"
title = re.findall(t_pttrn, line)
if len(title) != 0:
title = CleanData().clean_spc_articles(title[0])
rec_dict['TITLE'] = title
txt_pttrn = "<TEXT[^>]*>([\s\S]*?)</TEXT>"
text = re.findall(txt_pttrn, line)
if len(text) != 0:
text = CleanData().clean_spc_articles(text[0])
rec_dict['TEXT'] = text
#inserting each article into the database into the Articles collection
ConnectDb().insert_data(rec_dict, self.connect, 'ReuterDb',
'Articles')
def process_data(self):
#function that cleans the fetched tweets and inserts into processdb
data = ConnectDb().find_data(self.connect, 'RawDb', 'RawTweets')
for value in data:
processed_data = {}
for prop in value:
if (isinstance(value[prop], bson.objectid.ObjectId)) | (
value[prop] == None):
if value[prop] == None:
processed_data[prop] = value[prop]
else:
try:
formatted = CleanData().clean_emoji_data(
value[prop]) #remove emoji
clean_url = CleanData().clean_url_data(
formatted) #remove url
clean_spc = CleanData().clean_spc_chars(
clean_url) #remove special characters
processed_data[prop] = clean_spc
except:
pass
#insert cleaned data into process db
ConnectDb().insert_data(processed_data, self.connect, 'ProcessDb',
'Tweets')
def predict(self):
X = self.__X_test.drop('rent_amount_boxcox',axis=1)
y = self.__X_test['rent_amount_boxcox']
ypred = self.__xgbRegression.predict(X)
print('MAE:', metrics.mean_absolute_error(y, ypred))
print('MSE:', metrics.mean_squared_error(y, ypred))
print('RMSE:', np.sqrt(metrics.mean_squared_error(y, ypred)))
print('r2_score:', metrics.r2_score(y, ypred))
""" def test(self, lambda_):
test_data = np.array([2, 1, 4, 2, 3, 0, 1, 0, 1, 5, 3, 2, 10])
ypred = self.__linearRegression.predict(test_data)
scipy.special.inv_boxcox(ypred, lambda_) """
start = time.time()
clean_data = CleanData("house_price.csv")
data = clean_data.fit()
encode_data = EncodeData(data)
data = encode_data.fit()
corr = Correlation(data)
data = corr.corr_fit()
split = SplitData(data)
X, x = split.fit()
para_x = split.getParameters()
print(para_x)
xgb = XGBReg(X, x)
xgb.fit_()
xgb.predict()
print("Total time taken:", time.time() - start)
from download_data import vars_to_pull
from clean_data import CleanData
from analyze_data import Results, initial_data
from analyze_data_sklearn import SkLearnResults, init_data
from linear_regression_analysis import LinearData
if __name__ =='__main__':
data_cleaner = CleanData(vars_to_pull, is_test=True)
# Note: downloading all data can take 12+ hours
# Will skip if data exists (if partial download occured must move files for fresh download)
data_cleaner.run_download()
data_cleaner.clean_data()
# Calculating residuals can take 30+ minutes
results = Results(initial_data)
results.run_analyze()
sklresults = SkLearnResults(init_data)
sklresults.run_sk_analysis()
lrd = LinearData(init_data)
lrd.run_linear_analysis()
def plot_feature_size(num_iter):
"""Tests various feature sizes and plots the error.
Args:
num_iter: Number of times to test for each point.
"""
points = [100, 500, 1000, 2000, 3000, 4000, 5000, 6000, 7000,
8000, 9000, 10000]
errors = []
train_errors = []
# Iterate over all points defined.
for point in points:
print "Testing for point", point, "features."
error = 0
train_error = 0
# Repeat the test the desired number of times.
for i in range(0, num_iter):
cd = CleanData(tfidf=True, max_train_size=25000, max_features=point)
try:
# Get and train data.
training_data = cd.bag_of_words(in_file="data/clean_train_input.csv")
ids, X, y = get_numpy_matrices(training_data)
del training_data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=0)
del X, y, ids
nb = NaiveBayes()
nb.train(X_train, y_train)
# Calculate training and validation errors.
out = nb.classify(X_test)
error += nb.compute_error(out, y_test)
train_out = nb.classify(X_train)
train_error += nb.compute_error(train_out, y_train)
except MemoryError:
print "Memory error. Continuing."
continue
del X_train, X_test, y_train, y_test
errors.append(error / num_iter)
train_errors.append(train_error / num_iter)
# PLOT.
plt.figure(2)
plt.title("Error vs Features")
plt.xlabel("Number of features")
plt.ylabel("Error")
# plt.xscale('log')
plt.plot(points, errors, '-ro')
plt.plot(points, train_errors, '-bo')
plt.show()
print "Training Naive Bayes classifier."
nb.train(X_train, y_train)
print "Done training."
print "Classifying training input."
out = nb.classify(X_train)
print "Training error:", nb.compute_error(out, y_train)
# Clean up unused arrays.
del out
del y_train
del X_train
if __name__ == '__main__':
cd = CleanData(tfidf=True, max_train_size=15000, max_features=7000)
nb = NaiveBayes()
train_naive_bayes(cd, nb)
# Classify the test data.
classify_test_data(cd, nb, "results/nb_predictions2.csv")
# Tests.
# plot_max_train_size(3)
# plot_feature_size(3)
print "Completed successfully."
columns.remove("rent_amount_boxcox")
test_data = np.array([2, 1, 4, 2, 3, 0, 1, 0, 1, 5, 3, 2, 91]).T
index = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
df = pd.DataFrame(test_data, index=index, columns=columns)
#for i in range(len(self.__X_train.columns)):
# df.loc[0, df.columns[i]] = test[i]
#ypred = self.__model.predict(test_data)
#return scipy.special.inv_boxcox(ypred, lambda_)
return df """
start = time.time()
clean_data = CleanData("NO-CHANGES\hyd_v2.csv")
data = clean_data.fit()
encode_data = EncodeData(data)
data = encode_data.fit()
corr = Correlation(data)
data = corr.corr_fit()
split = SplitData(data)
X, x = split.fit()
xgb_ = XGBReg(X, x)
print(xgb_.fit_())
choice = input("Enter do you want to save this model.....type 'yes' to save or 'no' to ignore: ")
choice = choice.lower()
if choice == 'yes':
xgb_.save_XGBmodel()
else:
from sklearn import svm from clean_data import CleanData __author__ = "Yacine Sibous" cd = CleanData() print "Getting the training data." training_data = cd.bag_of_words(in_file="data/clean_train_input.csv") print "Done collecting data." X = [x[1] for x in training_data] y = [y[2] for y in training_data] print X[0:5] print y[0:5] clf = svm.SVC() clf.fit(X, y)
from sklearn import svm from sklearn.cross_validation import cross_val_score from clean_data import CleanData import numpy as np import csv __author__ = "Yacine Sibous, Jana Pavlasek" # Initialize data for final submission. cd = CleanData(tfidf=True, max_features=2500000, n_grams=3) # Geat features and output. print 'Getting Training data.' X, y = cd.bag_of_words(in_file="data/clean_train_input.csv", sparse=True) print 'Done collecting data.' # Train. print 'Training the model.' lin_clf = svm.LinearSVC() lin_clf.fit(X, y) print 'Done training.' # 3-fold cross validation. print 'Cross Validation' c_validation = cross_val_score(lin_clf, X, y, scoring='accuracy') print c_validation.mean() # Get and predict on the final test data. print 'Collecting test data.' test = cd.get_x_in(sparse=True) print 'Done collecting data.'
import folium
from folium import plugins
from folium.plugins import MarkerCluster
from clean_data import CleanData
met_df = CleanData()
m = folium.Map(zoom_start=4, tiles="OpenStreetMap")
cluster_map = MarkerCluster().add_to(m)
# Create an individual marker for each meteorite, adding it to a cluster
for coord in [tuple(x) for x in met_df.to_records(index=False)]:
ID = coord[1]
name = coord[0]
year = coord[6]
mass = coord[4]
rec_class = coord[3]
latitude = coord[7]
longitude = coord[8]
# Manually generate row index
#index = met_df[(met_df["reclat"] == latitude) & (met_df["reclong"] == longitude)].index.tolist()[0]
# Create custom marker icon | causes size increase of output html file
#meteorite_icon = folium.features.CustomIcon('Assets/meteorite.png', icon_size=(80,80))
html = f"""
<table border="1">
<tr>
<th> ID </th>