def frac_time(): urls, reqmap = get_data.getData() reqmap = sorted(reqmap, key=lambda x: return x['totalTime']) display_urls = reqmap[:10] return display_urls
def computeFraction( poi_messages, all_messages ):
""" given a number messages to/from POI (numerator)
and number of all messages to/from a person (denominator),
return the fraction of messages to/from that person
that are from/to a POI
"""
### you fill in this code, so that it returns either
### the fraction of all messages to this person that come from POIs
### or
### the fraction of all messages from this person that are sent to POIs
### the same code can be used to compute either quantity
### beware of "NaN" when there is no known email address (and so
### no filled email features), and integer division!
### in case of poi_messages or all_messages having "NaN" value, return 0.
fraction = 0.
for key in data_dict:
plt.scatter( data_dict[key]['fraction_to_poi'], data_dict[key]['fraction_from_poi'], color = 'b')
if data_dict[key]['poi'] == True:
plt.scatter(data_dict[key]['fraction_to_poi'], data_dict[key]['fraction_from_poi'], color='r', marker="*")
plt.ylabel('fraction of emails of this person to POI')
plt.xlabel('fraction of emails of this person from POI')
plt.show()
return fraction
data_dict = getData()
submit_dict = {}
for name in data_dict:
data_point = data_dict[name]
print
from_poi_to_this_person = data_point["from_poi_to_this_person"]
to_messages = data_point["to_messages"]
fraction_from_poi = computeFraction( from_poi_to_this_person, to_messages )
print fraction_from_poi
data_point["fraction_from_poi"] = fraction_from_poi
from_this_person_to_poi = data_point["from_this_person_to_poi"]
from_messages = data_point["from_messages"]
fraction_to_poi = computeFraction( from_this_person_to_poi, from_messages )
print fraction_to_poi
submit_dict[name]={"from_poi_to_this_person":fraction_from_poi,
"from_this_person_to_poi":fraction_to_poi}
data_point["fraction_to_poi"] = fraction_to_poi
#####################
def submitDict():
return submit_dict
def __init__(self, size, batch, dataset = getData(), train=0.7, val=0.0, test=0.3): self.dataset = dataset train = int(train*size) valid = int(val*size) self.size = size self.batch_size = int(batch) self.train = self.dataset[0:train] # self.valid = self.dataset[t:t+v] self.test = self.dataset[train:]
def __init__(self, size, batch, train=0.7, val=0.1, test=0.2): self.dataset = getData() t = int(train*size) v = int(val*size) self.size = size self.batch_size = int(batch) self.train = self.dataset[0:t] self.valid = self.dataset[t:t+v] self.test = self.dataset[t+v:]
def data_collection():
while(1):
hum, temp, soil, ldr = getData(ser)
time_read = datetime.now()
q.put(hum)
q.put(temp)
q.put(soil)
q.put(ldr)
q.put(time_read.strftime("%H:%M"))
def load_n_save(config_path):
'''
loads the data from the config_path using the
functions from get_data.py file
and saves to the data folder
'''
config = read_params(config_path)
df = getData(config_path)
# a liitle preprocessing for changing the name of the columns
# because the names have spaces between them which can cause issues
# in the future
up_cols = [col.replace(" ","_") for col in df.columns]
raw_path = config["load_data"]["raw_dataset"]
df.to_csv(raw_path, sep=",", index=False, header=up_cols)
### you fill in this code, so that it returns either
### the fraction of all messages to this person that come from POIs
### or
### the fraction of all messages from this person that are sent to POIs
### the same code can be used to compute either quantity
### beware of "NaN" when there is no known email address (and so
### no filled email features), and integer division!
### in case of poi_messages or all_messages having "NaN" value, return 0.
fraction = 0.
return fraction
data_dict = getData()
submit_dict = {}
for name in data_dict:
data_point = data_dict[name]
print
from_poi_to_this_person = data_point["from_poi_to_this_person"]
to_messages = data_point["to_messages"]
fraction_from_poi = computeFraction(from_poi_to_this_person, to_messages)
print fraction_from_poi
data_point["fraction_from_poi"] = fraction_from_poi
from_this_person_to_poi = data_point["from_this_person_to_poi"]
from_messages = data_point["from_messages"]
# -*- coding: utf-8 -*-
"""
Created on Sat Oct 24 15:26:55 2015
@author: Animesh, Laura, Minal, Shweta and Vasavi
"""
import get_ids
import get_data
d = {}
url = "../data/SearchForAtlantaZillow.xml"
API_key = 'X1-ZWz1a2hjdxu77v_305s0'
id_list = get_ids.getIds(url)
d = get_data.getData(id_list, API_key,d)
print d
# no filled email features), and integer division!
# in case of poi_messages or all_messages having "NaN" value, return 0.
fraction = 0.
if all_messages == 'NaN':
return fraction
if poi_messages == 'NaN':
poi_messages = 0
fraction = float(poi_messages)/float(all_messages)
return fraction
data_dict = getData()
submit_dict = {}
for name in data_dict:
data_point = data_dict[name]
print
from_poi_to_this_person = data_point["from_poi_to_this_person"]
to_messages = data_point["to_messages"]
fraction_from_poi = computeFraction( from_poi_to_this_person, to_messages )
print fraction_from_poi
data_point["fraction_from_poi"] = fraction_from_poi
from_this_person_to_poi = data_point["from_this_person_to_poi"]
from_messages = data_point["to_messages"]
from math import pi, sqrt, sin, cos
import scipy.constants as constants
from scipy import optimize
import get_data
INTEGRITY_CONSTANT = 0
LIGHT_SPEED = constants.c
GM = 3.98603 * (10**14)
OMEGA = 7.3 / (10**5)
# data = get_data.getData('irkutsk', 'etalon2') vv
data = get_data.getData('mendeleevo2', 'etalon2') # vv
# data = get_data.getData('irkutsk', 'cryosat2') x
# data = get_data.getData('mendeleevo2', 'cryosat2') x
# data = get_data.getData('irkutsk', 'swarm_A') x
# data = get_data.getData('mendeleevo2', 'swarm_A') x
# data = get_data.getData('irkutsk', 'KOMPSAT_5') x
# data = get_data.getData('mendeleevo2', 'KOMPSAT_5') x
# data = get_data.getData('irkutsk', 'QZS_1') v
# data = get_data.getData('mendeleevo2', 'QZS_1') ll
# data = get_data.getData('irkutsk', 'RadioAstron') v
# data = get_data.getData('mendeleevo2', 'RadioAstron') vv
fi_0 = data['longitude'] # fi_0
fi = 0 # fi
r_0 = 6371302 + data['radial_distance'] # R_0
a = data['a'] # a
e = data['eccentricity'] # e
theta_0 = data['latitude'] # theta_0
theta = data['inclination'] # theta
from sklearn import svm, tree from sklearn.svm import LinearSVC, SVC from sklearn.ensemble import RandomForestClassifier import tensorflow as tf from sklearn.datasets import load_digits from sklearn.model_selection import train_test_split, validation_curve, learning_curve from sklearn.neural_network import MLPClassifier from sklearn.preprocessing import LabelBinarizer, StandardScaler import numpy as np from sklearn.linear_model import Perceptron import matplotlib.pyplot as plt from get_data import getData [X, y] = getData() # scaler = StandardScaler() scaler.fit(X) x_train_std = scaler.transform(X) # X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5, shuffle=True) M1 = [1, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 1] M2 = [1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1] M3 = [0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1] M4 = [1, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0] M5 = [0, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1] Mystery = [M1, M2, M3, M4, M5] ppn = Perceptron(n_iter=40, eta0=0.1, random_state=0)
from sklearn import linear_model from get_data import getData features, labels = getData() clf = linear_model.Lasso(alpha=0.1) clf.fit(features)
sw.draw_chart_values(sw.comp_sym_spy.iloc[:10].spy_stock_comp)
# day week month statistics
# elif itype == "ds":
# pass
# uptrend sectors in each month
elif itype == "tspy":
sw.ss.sectors_uptrend_by_month()
# find bottom of the stocks when spy is going down
elif itype == "fb":
sw.find_bottom()
# download ernings
elif itype == "de":
gd = getData()
gd.get_earnings()
# download prices
elif itype == "dd":
gd = getData()
gd.start_download(interval, utc.localize(
datetime.now() - timedelta(days=365)))
# show earning dates
elif itype == "se":
sw.show_earning_dates(sw.db.time_from, sw.db.time_to, symbols = sw.symbols)
# show stats for specific stocks
elif itype == "ss":
sw.show_fin_earn_price(sym = sw.symbols)
