would anyone advise me how to adjust the X axis to better display the date on this graph?
from math import pi
import pandas as pd
from bokeh.io import show
from bokeh.models import LinearColorMapper, BasicTicker, PrintfTickFormatter, ColorBar
from bokeh.plotting import figure
#cesta k souboru
path = "C://Users//Zemi4//Desktop//zpr3//all2.csv"
#nacteni dataframu
data = pd.read_csv(path, delimiter = ",")
data['Cas'] = data['Cas'].astype(str)
data = data.set_index('Cas')
data.columns.name = 'Mistnost'
times = list(data.index)
rooms = list(data.columns)
df = pd.DataFrame(data.stack(), columns=['float']).reset_index()
colors = ['#440154', '#404387', '#29788E', '#22A784', '#79D151', '#FDE724', '#FCFEA4', '#FBA40A', '#DC5039']
mapper = LinearColorMapper(palette=colors, low=df.float.min(), high=df.float.max())
TOOLS = "hover,save,pan,box_zoom,reset,wheel_zoom"
p = figure(title="Heatmap ({0} - {1})".format(times[0], times[-1]),
x_range=times, y_range=list(reversed(rooms)),
x_axis_location="above", plot_width=1500, plot_height=900,
tools=TOOLS, toolbar_location='below',
tooltips=[('Time: ', '#Cas'), ('Temperature: ', '#float'), ('Room: ', '#Mistnost')],
x_axis_type='datetime')
p.grid.grid_line_color = None
p.axis.axis_line_color = None
p.axis.major_tick_line_color = None
p.axis.major_label_text_font_size = "5pt"
p.axis.major_label_standoff = 0
p.xaxis.major_label_orientation = pi / 3
p.rect(x="Cas", y="Mistnost", width=1, height=1,
source=df,
fill_color={'field': 'float', 'transform': mapper},
line_color=None)
color_bar = ColorBar(color_mapper=mapper, major_label_text_font_size="5pt",
ticker=BasicTicker(desired_num_ticks=len(colors)),
formatter=PrintfTickFormatter(format="%f"),
label_standoff=6, border_line_color=None, location=(0, 0))
p.add_layout(color_bar, 'right')
show(p) # show the pl
Try: p.xaxis[0].ticker.desired_num_ticks = <number_ticks_you_want_to_display>.
Or apply a specific ticker (see Bokeh docs) like you did for the ColorBar.
Related
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates as dates
import numpy as np
dt = pd.read_csv("C:\Subhro\ML_Internship\MARUTI_2.csv")
data = pd.DataFrame(dt)
data = data.drop('Date',axis=1)
data.drop(['Unnamed: 0'],axis=1,inplace=True)
print(data)
Roll_Mean_14 = data['Close Price'].rolling(window=14).mean()
Standard_Dev_14 = data['Close Price'].rolling(window=14).mean().std()
Upper_Band_14 = data['Close Price'].rolling(window=14).mean() + (2*Standard_Dev_14)
Low_Band_14 = data['Close Price'].rolling(window=14).mean() - (2*Standard_Dev_14)
avg_stock_price = data['Average Price']
stock_price = data['Close Price']
data['Roll_Avg'] = Roll_Mean_14
data['Upper_Band'] = Upper_Band_14
data['Lower_Band'] = Low_Band_14
data['Avg_Stock_Price'] = avg_stock_price
data=data.drop(data.head(14).index, inplace=False)
print(data)
for i in (data):
if((data['Close Price'][i])<(data['Lower_Band'][i])):
data['Call'][i]='Buy'
elif((data['Close Price'][i])>(data['Lower Band'][i])) and ((data['Close Price'][i])<(data['Roll_Avg'])):
data['Call'][i]='Hold Buy/Liquidate Short'
elif((data['Close Price'][i])>(data['Roll_Avg'][i])) and ((data['Close Price'][i])<(data['Upper Band'])):
data['Call'][i]='Hold Short/Liquidate Buy'
elif((data['Close Price'][i])>(data['Upper_Band'])):
data['Call'][i]='Short'
print(data)
In this code, I have been creating a new column : 'Call' to print the categories 'Buy','Short','Hold Buy/Liquidate Short', 'Hold Short/Liquidate Buy' according to the conditions given in the code. On running the code it is showing me the error as
KeyError : 'Symbol' in line
if((data['Close Price'][i])<(data['Lower_Band'][i])):
Your manner of accessing the indexes of the dataframe is incorrect.
You could try this :
for i in data.index:
if((data[i]['Close Price'])<(data[i]['Lower_Band'])):
The way you access a particular value(cell) in a dataframe(table) is :
data[row_index][column_index]
I am scraping names, prices and images from this website. There are 8 items in total, but in the DF I would like to filter only the items that contain the pattern "Original Zaino Antifurto". When I try to apply the bp_filter to the DF I get an error, probably due to hidden characters.
Does anyone know how to filter for this pattern avoiding the error?
import requests
from bs4 import BeautifulSoup
import pandas as pd
url_xd = 'https://www.xd-design.com/it-it/catalogsearch/result/?q=Bobby+Original+Zaino+Antifurto'
req_xd = requests.get(url_xd)
pars_xd = BeautifulSoup(req_xd.content, 'html.parser')
con_xd = pars_xd.find_all('div', class_ = 'product details product-item-details')
names_xd = []
prices_xd = []
picts_xd = []
for container in con_xd:
name = container.find("a", class_="product-item-link").text
names_xd.append(name)
for container in con_xd:
price = container.find("span", class_="price").text
prices_xd.append(price)
for container in con_xd:
pict = container.find("a").get("href")
picts_xd.append(pict)
bp_xd = pd.DataFrame({'(XD-Design) Item_Name': names_xd,
'Item_Price_EUR': prices_xd,
'Link_to_Pict': picts_xd })
bp_xd['Item_Price_EUR'] = bp_xd['Item_Price_EUR'].str.replace('€','').str.replace(',','.').astype(float)
bp_xd['(XD-Design) Item_Name'] = bp_xd['(XD-Design) Item_Name'].str.strip()
bp_filter = bp_xd['(XD-Design) Item_Name'][bp_xd['(XD-Design) Item_Name'].str.contains('Original Zaino Antifurto')]
# bp_xd[bp_filter]
Here you have the fixed working code
import requests
from bs4 import BeautifulSoup
import pandas as pd
url_xd = 'https://www.xd-design.com/it-it/catalogsearch/result/?q=Bobby+Original+Zaino+Antifurto'
req_xd = requests.get(url_xd)
pars_xd = BeautifulSoup(req_xd.content, 'html.parser')
con_xd = pars_xd.find_all('div', class_ = 'product details product-item-details')
names_xd = [c.find("a", class_="product-item-link").text for c in con_xd]
prices_xd = [c.find("span", class_="price").text for c in con_xd]
picts_xd = [c.find("a").get("href") for c in con_xd]
df = pd.DataFrame({'(XD-Design) Item_Name': names_xd,
'Item_Price_EUR': prices_xd,
'Link_to_Pict': picts_xd })
df['Item_Price_EUR'] = df['Item_Price_EUR'].str.replace('€','').str.replace(',','.').astype(float)
df['(XD-Design) Item_Name'] = df['(XD-Design) Item_Name'].str.strip()
df = df.loc[df['(XD-Design) Item_Name'].apply(lambda x: 1 if 'Original Zaino Antifurto' in x else 0) == 1]
I am getting familiar with scikit and its pandas integration using the Titanic tutorial on Kaggle. I have cleaned my data and would like to make some prediction. I can do it calling a pipeline fit and transform - unfortunately I get an error trying to do the same with cross_val_score.
I am using the sklearn-pandas cross_val_score
The code is as follows:
mapping = [
('Age', None),
('Embarked',LabelBinarizer()),
('Fare',None),
('Pclass',LabelBinarizer()),
('Sex',LabelBinarizer()),
('Group',LabelBinarizer()),
('familySize',None),
('familyType',LabelBinarizer()),
('Title',LabelBinarizer())
]
pipe = Pipeline([
('featurize', DataFrameMapper(mapping)),
('logReg', LogisticRegression())
])
X = df_train[df_train.columns.drop('Survived')]
y = df_train['Survived']
#model = pipe.fit(X = X, y = y)
#prediction = model.predict(df_train)
score = cross_val_score(pipe, X = X, y = y, scoring = 'accuracy')
df_train is a Pandas dataframe containing all my training set, including outcomes. The two commented lines:
model = pipe.fit(X = X, y = y)
prediction = model.predict(df_train)
Work fine and prediction returns me an array with predicted outcomes. Using the same with cross_val_score, I get the following error:
X has 20 features per sample; expecting 19
Full code below, can be run with the Titanic CSV files on Kaggle (https://www.kaggle.com/c/titanic/data)
#%% Libraries import
import pandas as pd
import numpy as np
from sklearn_pandas import DataFrameMapper, cross_val_score
from sklearn.preprocessing import LabelBinarizer
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression
#%% Read the data
path = 'E:/Kaggle/Titanic/Data/'
file_training = 'train.csv'
file_test = 'test.csv'
#Import the training and test dataset and concatenate them
df_training = pd.read_csv(path + file_training, header = 0, index_col = 'PassengerId')
df_test = pd.read_csv(path + file_test, header = 0, index_col = 'PassengerId')
# Work on the concatenated training and test data for feature engineering and clean-up
df = pd.concat([df_training, df_test], keys = ['train','test'])
#%% Initial data exploration and cleaning
df.describe(include = 'all')
pd.isnull(df).sum() > 0
#%% Preprocesing and Cleanup
#Create new columns with the name (to identify individuals part of a family)
df['LName'] = df['Name'].apply(lambda x:x.split(',')[0].strip())
df['FName'] = df['Name'].apply(lambda x:x.split(',')[1].split('.')[1].strip())
#Get the title
df['Title'] = df['Name'].apply(lambda x:x.split(',')[1].split('.')[0].strip())
titleDic = {
'Master' : 'kid',
'Mlle' : 'unmarriedWoman',
'Miss' : 'unmarriedWoman',
'Ms' : 'unmarriedWoman',
'Jonkheer' : 'noble',
'Don' : 'noble',
'Dona' : 'noble',
'Sir' : 'noble',
'Lady' : 'noble',
'the Countess' : 'noble',
'Capt' : 'ranked',
'Major' : 'ranked',
'Col' : 'ranked',
'Mr' : 'standard',
'Mme' : 'standard',
'Mrs' : 'standard',
'Dr' : 'academic',
'Rev' : 'academic'
}
df['Group'] = df['Title'].map(titleDic)
#%% Working with the family size
#Get the family size
df['familySize'] = df['Parch'] + df['SibSp'] + 1
#Add a family tag (single, couple, small, large)
df['familyType'] = pd.cut(df['familySize'],
[1,2,3,5,np.inf],
labels = ['single','couple','sFamily','bFamily'],
right = False)
#%% Filling empty values
#Fill empty values with the mean or mode for the column
#Fill the missing values with mean for age per title, class and gender. Store value in AgeFull variable
agePivot = pd.DataFrame(df.groupby(['Group', 'Sex'])['Age'].median())
agePivot.columns = ['AgeFull']
df = pd.merge(df, agePivot, left_on = ['Group', 'Sex'], right_index = True)
df.loc[df['Age'].isnull(),['Age']] = df['AgeFull']
#Embark location missing values
embarkPivot = pd.DataFrame(df.groupby(['Group'])['Embarked'].agg(lambda x:x.value_counts().index[0]))
embarkPivot.columns = ['embarkFull']
df = pd.merge(df, embarkPivot, left_on = ['Group'], right_index = True)
df.loc[df['Embarked'].isnull(),['Embarked']] = df['embarkFull']
#Fill the missing fare value
df.loc[df['Fare'].isnull(), 'Fare'] = df['Fare'].mean()
#%% Final clean-up (drop temporary columns)
df = df.drop(['AgeFull', 'embarkFull'], 1)
#%% Preparation for training
df_train = df.loc['train']
df_test = df.loc['test']
#Creation of dummy variables
mapping = [
('Age', None),
('Embarked',LabelBinarizer()),
('Fare',None),
('Pclass',LabelBinarizer()),
('Sex',LabelBinarizer()),
('Group',LabelBinarizer()),
('familySize',None),
('familyType',LabelBinarizer()),
('Title',LabelBinarizer())
]
pipe = Pipeline(steps = [
('featurize', DataFrameMapper(mapping)),
('logReg', LogisticRegression())
])
#Uncommenting the line below fixes the code - why?
#df_train = df_train.sort_index()
X = df_train[df_train.columns.drop(['Survived'])]
y = df_train.Survived
score = cross_val_score(pipe, X = df_train, y = df_train.Survived, scoring = 'accuracy')
This is very interesting. I have solved the issue just by sorting using the index the DataFrame before passing it to the cross_val_score in the pipeline.
df_train = df_train.sort_index()
Could anyone explain me why this would have an impact on how Scikit is working?
When I try to execute a simple crossover strategy algorithm outside quantopian framework using zipline, I get the following error.
KeyError: <type 'zipline.assets._assets.Equity'>
This is a simple crossover strategy where 50-100 day moving averages are calculated to derive trading strategy. I am unable to run this strategy out of Quantopian framework using zipline.
Code is as follows
import pandas as pd
import zipline
from zipline import TradingAlgorithm
from zipline.api import order, sid
from zipline.utils.factory import load_from_yahoo
import matplotlib.pyplot as plt
from zipline.api import order, symbol, record, order_target
import pytz
%matplotlib inline
# creating time interval
start = pd.Timestamp('2013-01-25', tz='UTC')
end = pd.Timestamp('2017-02-01', tz='UTC')
#input_date = get_pricing(['AAPL'],start,end,frequency='daily')
# loading the data
#input_data = load_bars_from_yahoo(stocks=['AAPL'], start=start,end=end,)
data = load_from_yahoo(stocks=['AAPL'], indexes={}, start=start, end=end)
data = data.dropna()
def initialize(context):
context.security= symbol('AAPL')
context.i =0
def handle_data(context, data):
context.i += 1
if context.i<100:
return
MA1 = data[context.security].mavg(50)
MA2 = data[context.security].mavg(100)
date = str(data[context.security].datetime)[:10]
current_price = data[context.security].price
current_positions = context.portfolio.positions[symbol('AAPL')].amount
cash = context.portfolio.cash
value = context.portfolio.portfolio_value
current_pnl = context.portfolio.pnl
if (MA1 > MA2) and current_positions == 0:
number_of_shares = 100
order(context.security, number_of_shares)
record(AAPL=inputdata[symbol('AAPL')].price,date=date,MA1 = MA1, MA2 = MA2, Price=
current_price,status="buy",shares=number_of_shares,PnL=current_pnl,cash=cash,value=value)
elif (MA1 < MA2) and current_positions != 0:
order_target(context.security, 0)
record(AAPL=inputdata[symbol('AAPL')].price,date=date,MA1 = MA1, MA2 = MA2, Price= current_price,status="sell",shares="--",PnL=current_pnl,cash=cash,value=value)
else:
record(AAPL=inputdata[symbol('AAPL')].price,date=date,MA1 = MA1, MA2 = MA2, Price= current_price,status="--",shares="--",PnL=current_pnl,cash=cash,value=value)
algo = TradingAlgorithm(initialize=initialize, handle_data=handle_data)
results = algo.run(input_data)
use codes as below to calculate MA1 and MA2, then it works!
because some of the function is out of date in zipline 1.1.0
from talib import MA
trailing_window = data.history(assets=context.security, fields='price', bar_count=100, frequency='1d')
MA1 = MA(trailing_window.values, 50)[-1]
MA2 = MA(trailing_window.values, 100)[-1]
or use the codes as below without using talib:
trailing_window1 = data.history(assets=context.security, fields='price', bar_count=50, frequency='1d')
trailing_window2 = data.history(assets=context.security, fields='price', bar_count=100, frequency='1d')
MA1 = trailing_window1.mean()
MA2 = trailing_window2.mean()
I'm trying to create one dataframe with data from multiple urls I'm scraping. The code works however I'm unable to store the data in one DataFrame recursively. The DataFrame (called frame) is replaced with a new url's data each time rather than having the new data concatenated to the same frame. Thank you, I deeply appreciate your help!
import urllib
import re
import json
import pandas
import pylab
import numpy
import matplotlib.pyplot
from pandas import *
from pylab import *
from threading import Thread
import sqlite3
urls = ['http://www.ratemyprofessors.com/ShowRatings.jsp?tid=1176131' , 'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=795226', 'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=1176131' , 'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=1807944', 'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=277459' , 'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=1076779' , 'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=971546']
i=0
regex = '<p class="commentText">(.+?)</p>'
regex2 = '<strong>Easiness</strong><span>(.+?)</span></p>'
regex3 = 'Helpfulness</strong><span>(.+?)</span></p>'
regex4 = 'Clarity</strong><span>(.+?)</span></p>'
regex5 = 'Rater Interest</strong><span>(.+?)</span></p>'
regex6 = '<div class="date">(.+?)</div>'
regex7 = '<div class="class"><p style="word-wrap:break-word;">(.+?)</p>'
regex8 = '<meta name="prof_name" content="(.+?)"/>'
pattern = re.compile(regex)
easiness = re.compile(regex2)
helpfulness = re.compile(regex3)
clarity = re.compile(regex4)
interest = re.compile(regex5)
date = re.compile(regex6)
mathclass = re.compile(regex7)
prof_name = re.compile(regex8)
while i < len(urls):
htmlfile = urllib.urlopen(urls[i])
htmltext = htmlfile.read()
content = re.findall(pattern,htmltext)
Easiness = re.findall(easiness,htmltext)
Helpfulness = re.findall(helpfulness, htmltext)
Clarity = re.findall(clarity, htmltext)
Interest = re.findall(interest, htmltext)
Date = re.findall(date, htmltext)
Class = re.findall(mathclass, htmltext)
PROFNAME=re.findall(prof_name, htmltext)
i+=1
frame = DataFrame({'Comments': content, 'Easiness': Easiness, 'Helpfulness': Helpfulness,
'Clarity': Clarity, 'Rater Interest': Interest, 'Class': Class,
'Date': Date[1:len(Date)], 'Professor': PROFNAME[0]})
print frame
Use pd.concat:
frames = []
while i < len(urls):
htmlfile = urllib.urlopen(urls[i])
htmltext = htmlfile.read()
content = re.findall(pattern,htmltext)
Easiness = re.findall(easiness,htmltext)
Helpfulness = re.findall(helpfulness, htmltext)
Clarity = re.findall(clarity, htmltext)
Interest = re.findall(interest, htmltext)
Date = re.findall(date, htmltext)
Class = re.findall(mathclass, htmltext)
PROFNAME=re.findall(prof_name, htmltext)
i+=1
frames.append(DataFrame({'Comments': content, 'Easiness': Easiness, 'Helpfulness': Helpfulness,
'Clarity': Clarity, 'Rater Interest': Interest, 'Class': Class,
'Date': Date[1:len(Date)], 'Professor': PROFNAME[0]}))
pd.concat(frames)
You are overwriting your frame with each iteration of the loop. As Phillip Cloud suggested, you can make a list of frames that you append with each loop. I simplified your code differently, but I think this gives you what you want.
import urllib
import re
import pandas as pd
urls = ['http://www.ratemyprofessors.com/ShowRatings.jsp?tid=1176131',
'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=795226',
'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=1176131',
'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=1807944',
'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=277459',
'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=1076779',
'http://www.ratemyprofessors.com/ShowRatings.jsp?tid=971546']
regex = {'pattern' : re.compile('<p class="commentText">(.+?)</p>'),
'easiness' : re.compile('<strong>Easiness</strong><span>(.+?)</span></p>'),
'helpfulness' : re.compile('Helpfulness</strong><span>(.+?)</span></p>'),
'clarity' : re.compile('Clarity</strong><span>(.+?)</span></p>'),
'interest' : re.compile('Rater Interest</strong><span>(.+?)</span></p>'),
'date' : re.compile('<div class="date">(.+?)</div>'),
'mathclass' : re.compile('<div class="class"><p style="word-wrap:break-word;">(.+?)</p>'),
'prof_name' : re.compile('<meta name="prof_name" content="(.+?)"/>')}
# Make a dictionary with empty lists using the same keys
d = {}
for k in regex.keys():
d[k] = []
# Now fill those lists
for url in urls:
htmlfile = urllib.urlopen(url)
htmltext = htmlfile.read()
for k, v in regex.iteritems():
d[k].append(re.findall(v, htmltext))
frame = pd.DataFrame(d) # Dump the dict into a DataFrame
print frame