def bar_chart(self, conn, column1, column2, table_chosen, title): # since this is a bar graph only two columns will be there data_df = dfile.double_selector(conn = conn, table= table_chosen, col1 = column1, col2 = column2) bar_plot = ggplot(aes(x=column1, weight=column2), data=data_df) + geom_bar() + labs(title=title) print(bar_plot)
def two_var_intr_effects(self, target, vars, nval=100, plot=True):
""" Loads first level interactions.
Args:
target - Variable identifier (column name or number) specifying the
target variable
vars - List of variable identifiers (column names or numbers) specifying
other selected variables. Must not contain target
nval - Number of evaluation points used for calculation.
plot - Determines whether or not to plot results.
Returns: Pandas dataframe of interaction effects
"""
# Check if null.models have already been generated
check_str = """
function(){
if(exists("null.models")){
return(T)
} else {
return(F)
}
}
"""
if not robjects.r(check_str)()[0]:
self.logger.info(
'Null models not generated, generating null models '
'(n=10)')
self._generate_interaction_null_models(10, quiet=False)
int_str = """
function(target, vars, nval){
interactions <- twovarint(tvar=target, vars=vars, null.models,
nval=nval, plot=F)
}
"""
# Check the input type. If int, add one, if string do nothing.
target = target if type(target) is str else target + 1
vars = [var if type(var) is str else var + 1 for var in vars]
r_interact = robjects.r(int_str)(target,
robjects.Vector(np.array(vars)), nval)
interact = pd.DataFrame(
{
'interact_str': list(r_interact[0]),
'exp_null_int': list(r_interact[1]),
'std_null_int': list(r_interact[2])
},
index=vars)
if plot:
int_effects = interact.reset_index().rename(
columns={'index': 'vars'})
int_effects_m = pd.melt(
int_effects,
id_vars='vars',
value_vars=['interact_str', 'exp_null_int'])
p = gg.ggplot(gg.aes(x='vars', fill='variable', weight='value'),
data=int_effects_m) \
+ gg.geom_bar() \
+ gg.labs(
title='Two-var interaction effects - {}'.format(target))
print(p)
return interact
def plot_sfs(self, pat_out):
df = pd.DataFrame({
"freq": [i for i in range(1, len(self.sfs))],
"sfs": np.array(self.sfs[1:len(self.sfs)])
})
print df
pl = ggplot(df, aes(x="freq", weight="sfs")) + geom_bar()
pl.save(pat_out)
def plotAverageLatency(self):
averages = [d.averageLatency() for d in self.data]
dat = {"device": range(1, len(averages) + 1), "average": averages}
dataframe = pandas.DataFrame(dat)
chart = ggplot.ggplot(ggplot.aes(x="device", weight="average"), dataframe) \
+ ggplot.labs(title="Average Latency Per Device") + \
ggplot.ylab("Average Latency (ms)") + \
ggplot.xlab("Device Number") + \
ggplot.geom_bar(stat="identity")
chart.show()
def plotAverageLatency(self):
averages = [d.averageLatency() for d in self.data]
dat = { "device" : range(1, len(averages) + 1), "average" : averages }
dataframe = pandas.DataFrame(dat)
chart = ggplot.ggplot(ggplot.aes(x="device", weight="average"), dataframe) \
+ ggplot.labs(title="Average Latency Per Device") + \
ggplot.ylab("Average Latency (ms)") + \
ggplot.xlab("Device Number") + \
ggplot.geom_bar(stat="identity")
chart.show()
def _ggplot(df, out_file):
"""Plot faceted items with ggplot wrapper on top of matplotlib.
XXX Not yet functional
"""
import ggplot as gg
df["variant.type"] = [vtype_labels[x] for x in df["variant.type"]]
df["category"] = [cat_labels[x] for x in df["category"]]
df["caller"] = [caller_labels.get(x, None) for x in df["caller"]]
p = (gg.ggplot(df, gg.aes(x="caller", y="value.floor")) + gg.geom_bar() +
gg.facet_wrap("variant.type", "category") + gg.theme_seaborn())
gg.ggsave(p, out_file)
def _ggplot(df, out_file):
"""Plot faceted items with ggplot wrapper on top of matplotlib.
XXX Not yet functional
"""
import ggplot as gg
df["variant.type"] = [vtype_labels[x] for x in df["variant.type"]]
df["category"] = [cat_labels[x] for x in df["category"]]
df["caller"] = [caller_labels.get(x, None) for x in df["caller"]]
p = (gg.ggplot(df, gg.aes(x="caller", y="value.floor")) + gg.geom_bar()
+ gg.facet_wrap("variant.type", "category")
+ gg.theme_seaborn())
gg.ggsave(p, out_file)
def generate_intr_effects(self, nval=10, n=10, quiet=False, plot=True):
""" Loads R variable interaction effect objects
Args:
nval - Number of evaluation points used for calculation
n - Number of null models to generate for interaction calibaration
quiet - Determines whether to print intermediate data.
Returns: Pandas dataframe of interaction effects
"""
self._generate_interaction_null_models(n, quiet)
int_str = """
function(ncols, nval){
if(exists("null.models")){
interactions <- interact(c(1:ncols), null.models,
nval=nval,
plot=F)
} else {
interactions <- interact(c(1:ncols), nval=nval, plot=F)
}
}
"""
ncols = len(self._data['x'].columns.values)
r_interact = robjects.r(int_str)(ncols, nval)
interact = pd.DataFrame(
{
'interact_str': list(r_interact[0]),
'exp_null_int': list(r_interact[1]),
'std_null_int': list(r_interact[2])
},
index=self._data['x'].columns)
self._interaction_effects = interact
if plot:
int_effects = interact.reset_index().rename(
columns={'index': 'vars'})
int_effects_m = pd.melt(
int_effects,
id_vars='vars',
value_vars=['interact_str', 'exp_null_int'])
p = gg.ggplot(gg.aes(x='vars', fill='variable', weight='value'),
data=int_effects_m) \
+ gg.geom_bar() \
+ gg(title='Interaction Effects')
print(p)
def plotAlignmentStat(input, output):
"""plot Alignment summary using ggplot"""
df = pd.read_csv(input, thousands=",")
# replace % with '' and convert the type to float
#df.replace('%', '', regex=True)
print df.dtypes
# convert to numeric
#df1=df.apply(pd.to_numeric, args=('coerce',))
# Get certain rows
print df
df = df.iloc[[2, 4, 5], ]
#df = df.ix[['Uniquely mapped reads %', 'Number of reads mapped to multiple loci %', 'Reads unmapped: too short %']]
dfm = pd.melt(df,
id_vars=['category'],
var_name='sampleName',
value_name='Value')
print dfm
#from ggplot import *
#import pandas as pd
#df = pd.DataFrame({"x":[1,2,3,4], "y":[1,3,4,2]})
#ggplot(aes(x="x", weight="y"), df) + geom_bar()
#ggplot(diamonds, aes(x='price', fill='cut')) + geom_histogram() + theme_bw() + scale_color_brewer(type='qual')
from ggplot import ggplot, geom_bar, aes, theme_bw, ggtitle, coord_flip, geom_histogram #,scale_y_continuous,coord_flip
p = ggplot(dfm, aes(x='sampleName', weight='Value',
fill='category')) + geom_bar() + theme_bw() + ggtitle(
"Alignment Summary stats") + coord_flip(
) # + scale_y_continuous(labels='comma
#p = ggplot(dfm, aes(x='sampleName', weight='Value', fill='category')) + geom_bar(position = "stack", stat='identity') + theme_bw() + ggtitle("Alignment Summary stats") + coord_flip()# + scale_y_continuous(labels='comma') + coord_flip()
#p = ggplot(df, aes(x = "category", y = "value", fill = "variable")) + \
#geom_bar(stat="bar", labels=df["category"].tolist()) + \
#theme(axis_text_x = element_text(angle=90))
dirname, filename = os.path.split(output)
print dirname
print filename
p.save(output)
#ggsave(plot=p, filename=filename, path=dirname)
return
def graph2(score_data):
""" Average scores for each question on most recent date;
Creates and returns graph 2, a bar graph. """
date_column = score_data[0][find_time_stamp(score_data)]
columns_data = score_data[0]
for i in range(0, len(columns_data)):
columns_data[i] = columns_data[i].split('.')[0]
data = DataFrame(score_data[1:], columns=columns_data)
# Get all columns that are numerical questions so we know what to graph
num_questions = data.select_dtypes(include=['int64']).columns.values
# Melt data so that each question is in a seperate row
new_data = pd.melt(data,
id_vars=date_column,
value_vars=num_questions,
var_name="Question",
value_name="Score")
# Convert date string into actual data type
new_data[date_column] = pd.to_datetime(new_data[date_column],
format="%m/%d/%Y")
# Latest Dates
recent_date = new_data[date_column].max()
# Removing all dates that are recent
new_data = new_data[new_data.Timestamp == recent_date]
# Group all rows with question, and then take the average.
new_data = new_data.groupby(['Question']).mean().reset_index()
# Create bar graph with data from past week
ret = ggplot.ggplot(ggplot.aes(x="Question", weight="Score"), new_data) +\
ggplot.geom_bar() +\
ggplot.ggtitle("Most Recent Average Scores")
return ret
def plot1(data):
xvar = data['teamID' == 'SFN']
yvar = data['teamID' == 'LAN']
gg = ggplot(data, aes(xvar, yvar)) + geom_bar()
return gg
def plot_weather_data(turnstile_weather):
'''
You are passed in a dataframe called turnstile_weather.
Use turnstile_weather along with ggplot to make a data visualization
focused on the MTA and weather data we used in assignment #3.
You should feel free to implement something that we discussed in class
(e.g., scatterplots, line plots, or histograms) or attempt to implement
something more advanced if you'd like.
Here are some suggestions for things to investigate and illustrate:
* Ridership by time of day or day of week
* How ridership varies based on Subway station
* Which stations have more exits or entries at different times of day
If you'd like to learn more about ggplot and its capabilities, take
a look at the documentation at:
https://pypi.python.org/pypi/ggplot/
You can check out:
https://www.dropbox.com/s/meyki2wl9xfa7yk/\n
turnstile_data_master_with_weather.csv
To see all the columns and data points included in the turnstile_weather
dataframe.
However, due to the limitation of our Amazon EC2 server, we are giving
you about 1/3 of the actual data in the turnstile_weather dataframe
'''
df = turnstile_weather.copy()
# we will remove national holidays from the data. May 30 is Memorial Day,
# the only national holiday in our data set. Normally this would be done
# by passing in the data more elegantly, but since this is a bit more
# constrained, we will simply hard code it into the function.
national_holidays = ['2011-05-30']
for holiday in national_holidays:
df = df[df.DATEn != holiday]
# add a column to represent the ISO day of the week for each data point.
df[u'weekday'] = df[u'DATEn'].apply(\
lambda x: datetime.datetime.strptime(x, '%Y-%m-%d').isoweekday())
##now introduce a multiplier variable so that the ENTRIESn_hourly
##values can be modified when we have multiple data days. For example
##if we have 2 fridays with rain the multiplier is 1/2 so that summing
##the modified values will give us the average number of riders
##entering the subways system on a rainy friday.
for day in df.weekday.unique():
for rain_status in df.rain.unique():
# number of unique dates with the same weekday and rain status
u = df[(df.weekday == day) & (df.rain == rain_status)].\
DATEn.nunique()
if u != 0:
multiplier = float(1.0 / u)
else:
multiplier = 0
daily_sum = \
df[(df.weekday == day) & (df.rain == rain_status)].sum()
entries_sum = daily_sum.ENTRIESn_hourly
multiplier_index_list = \
df[(df.weekday == day) & (df.rain == rain_status)].index
df.loc[multiplier_index_list, u'ENTRIESn_hourly'] = \
multiplier * entries_sum
##now we have a dataframe wich is ready to be utilized for making our
##plot using the data contained within.
p = ggplot.ggplot(ggplot.aes(x = u'factor(weekday)', \
weight = u'ENTRIESn_hourly', \
fill = u'weekday'),\
data = df) +\
ggplot.geom_bar() +\
ggplot.facet_grid(x = u'rain', y = u'weekday') +\
ggplot.ggtitle('Average Ridership on Sunny & Rainy ISO Weekdays')
print p
return p
pd.to_datetime(re.sub(r'\scrop_small.png','', x),
format='%Y-%m-%dt%H%M'))
wormID = 0
data['lifeSpanHours'] = 0
data['lifeSpanDays'] = 0
data['elapsedHours'] = 0
data['elapsedDays'] = 0
data['wormID'] = ''
for iWorm in data['path'].unique():
data.loc[data['path'] == iWorm, 'lifeSpanDays'] = (data.loc[data['path'] == iWorm, 'date'].max()-data.loc[data['path'] == iWorm, 'date'].min()).days
data.loc[data['path'] == iWorm, 'lifeSpanHours'] = (data.loc[data['path'] == iWorm, 'date'].max()-data.loc[data['path'] == iWorm, 'date'].min()).seconds/3600 + data.loc[data['path'] == iWorm, 'lifeSpanDays'] * 24
data.loc[data['path'] == iWorm, 'elapsedDays'] = (data.loc[data['path'] == iWorm, 'date'] - data.loc[data['path'] == iWorm, 'date'].min())/(86400*1e9)
data.loc[data['path'] == iWorm, 'elapsedHours'] = (data.loc[data['path'] == iWorm, 'date'] - data.loc[data['path'] == iWorm, 'date'].min())/(3600*1e9)
data.loc[data['path'] == iWorm, 'wormID'] = '%d' % wormID
wormID += 1
data['lifeSpanDuration'] = pd.cut(data.lifeSpanDays, 2, labels=["short", "long"])
data.to_csv(dfFile, sep=',', encoding='utf-8', header=True, index=False)
data.lifeSpanDays.mean()
data.lifeSpanDays.max()
data.lifeSpanDays.min()
#dataMidPoint = data.loc[data['elapsedDays'] ==4 , :]
dataMidPoint = data.loc[data['elapsedDays'] ==1 , :]
dataMidPoint.to_csv(dfMidPointFile, sep=',', encoding='utf-8', header=True, index=False)
p = gg.ggplot(gg.aes(x='lifeSpanDuration'), data=dataMidPoint)
p + gg.geom_bar()
#####################################################################################
# Here is an example of using Rodeo:
# We'll use the popular package called Pandas
# Install it with pip
! pip install pandas
# Import it as 'pd'
import pandas as pd
# Create a dataframe
df=pd.DataFrame({"Animal":["dog","dolphin","chicken","ant","spider"],"Legs":[4,0,2,6,8]})
df.head()
#####################################################################################
# An example of making a plot:
! pip install ggplot
from ggplot import ggplot, aes, geom_bar
ggplot(df, aes(x="Animal", weight="Legs")) + geom_bar(fill='blue')
# Find this tutorial helpful? Checkout the blue sidebar for more tutorials!
import freegames
from turtle import *
from random import randrange
from freegames import square, vector
import os
from os.path import join, splitext, exists, abspath, basename
import pandas as pd
import pdb
import ggplot as ggp
import utils
log = utils.makeLogger('titanic-data-exploration')
# Load dataframe
DFN = abspath(join(os.curdir, os.pardir, 'datasets', 'titanic-train.csv'))
df = pd.read_csv(DFN)
log.debug("{} has columns: {}".format(basename(DFN), df.columns.tolist()))
# Plot exploratory data analysis
log.debug("Plotting exploratory slices")
pt = ggp.ggplot(ggp.aes(x='Sex', fill='Survived'), data=df) + \
ggp.geom_bar()
# NOTE type "pt" into the debugger to show the plot
pdb.set_trace()
# With ggplot
import ggplot as gg
df_ = df.copy()
df_["cat"] = df_.index
df_melted = df_.melt(id_vars=["cat"])
cm2 = gg.ggplot(df_melted, gg.aes(x="cat", fill="variable", y ="value"))
cm2 += gg.xlab("category") + gg.ylab("frequency") +\
gg.ggtitle("Confusion Matrix")
cm2 += gg.geom_bar(stat="identity", position="stack")
cm2
#%%
# With altair
import altair as alt
chart = alt.Chart(df_melted).mark_bar().encode(
x='cat',
y='value',
color='variable'
)
def plot_weather_data(turnstile_weather):
'''
You are passed in a dataframe called turnstile_weather.
Use turnstile_weather along with ggplot to make a data visualization
focused on the MTA and weather data we used in assignment #3.
You should feel free to implement something that we discussed in class
(e.g., scatterplots, line plots, or histograms) or attempt to implement
something more advanced if you'd like.
Here are some suggestions for things to investigate and illustrate:
* Ridership by time of day or day of week
* How ridership varies based on Subway station
* Which stations have more exits or entries at different times of day
If you'd like to learn more about ggplot and its capabilities, take
a look at the documentation at:
https://pypi.python.org/pypi/ggplot/
You can check out:
https://www.dropbox.com/s/meyki2wl9xfa7yk/\n
turnstile_data_master_with_weather.csv
To see all the columns and data points included in the turnstile_weather
dataframe.
However, due to the limitation of our Amazon EC2 server, we are giving
you about 1/3 of the actual data in the turnstile_weather dataframe
'''
df = turnstile_weather.copy()
# we will remove national holidays from the data. May 30 is Memorial Day,
# the only national holiday in our data set. Normally this would be done
# by passing in the data more elegantly, but since this is a bit more
# constrained, we will simply hard code it into the function.
national_holidays = ['2011-05-30']
for holiday in national_holidays:
df = df[df.DATEn != holiday]
# add a column to represent the ISO day of the week for each data point.
df[u'weekday'] = df[u'DATEn'].apply(\
lambda x: datetime.datetime.strptime(x, '%Y-%m-%d').isoweekday())
##now introduce a multiplier variable so that the ENTRIESn_hourly
##values can be modified when we have multiple data days. For example
##if we have 2 fridays with rain the multiplier is 1/2 so that summing
##the modified values will give us the average number of riders
##entering the subways system on a rainy friday.
for day in df.weekday.unique():
for rain_status in df.rain.unique():
# number of unique dates with the same weekday and rain status
u = df[(df.weekday == day) & (df.rain == rain_status)].\
DATEn.nunique()
if u != 0:
multiplier = float(1.0 / u)
else:
multiplier = 0
daily_sum = \
df[(df.weekday == day) & (df.rain == rain_status)].sum()
entries_sum = daily_sum.ENTRIESn_hourly
multiplier_index_list = \
df[(df.weekday == day) & (df.rain == rain_status)].index
df.loc[multiplier_index_list, u'ENTRIESn_hourly'] = \
multiplier * entries_sum
##now we have a dataframe wich is ready to be utilized for making our
##plot using the data contained within.
p = ggplot.ggplot(ggplot.aes(x = u'factor(weekday)', \
weight = u'ENTRIESn_hourly', \
fill = u'weekday'),\
data = df) +\
ggplot.geom_bar() +\
ggplot.facet_grid(x = u'rain', y = u'weekday') +\
ggplot.ggtitle('Average Ridership on Sunny & Rainy ISO Weekdays')
print p
return p
#! /usr/bin/env/ python
#================== This line is 79 spaces wide ==============================#
import ggplot
test_data = ggplot.mtcars.tail(15)
print test_data
##def average_weight(df, x_value, w_value):
## for x_item in df.x_value.unique():
## for w_item in df.w_value.unique():
## print df[(df.x_value == x_item) & (df.w_value == w_item)].sum()
##average_weight(test_data, 'cyl', 'carb')
p = ggplot.ggplot(ggplot.aes(x = 'factor(cyl)'), data = test_data) +\
ggplot.geom_bar()
## ggplot.facet_grid(x = u'cyl', y = u'gear')
print p
import ggplot as gg
import ultrasignup as us
import numpy as np
d = us.event_results(299)
p1 = gg.ggplot(
gg.aes(x='time_hour',fill='gender'),d[(d.distance=='50K')&(d.time_hour>1.0)]) + \
gg.facet_grid(x='gender') + \
gg.geom_bar(stat="bin",binwidth=.5,position="dodge",colour="black") + \
gg.xlab("Time (hours)") + gg.ylab("Number of Finishers") + \
gg.ggtitle("50K Finishing Times for All Years")
p2 = gg.ggplot(
gg.aes(x='time_hour',fill='gender'),d[(d.distance=='11 Miler')&(d.time_hour>1.0)]) + \
gg.facet_grid(x='gender') + \
gg.geom_bar(stat="bin",binwidth=.5,position="dodge",colour="black") + \
gg.xlab("Time (hours)") + gg.ylab("Number of Finishers") + \
gg.ggtitle("11M Finishing Times for All Years")
def second(dataframe):
plot = ggplot.ggplot(
ggplot.aes(x='Speed'),
data=dataframe) + ggplot.geom_bar(color='lightblue') + ggplot.ggtitle(
"Frequencies of Speeds Among Interfaces") + ggplot.theme_xkcd()
plot.show()
},
index=range(t * len(count_tops),
t * len(count_tops) + len(count_tops)))
probs_list.append(probs_t)
# Calculate KL divergences
kl_mle_list.append(stats.entropy(true_bins_t, mle_probs_vals))
kl_nn_list.append(stats.entropy(true_bins_t, nn_probs_t))
probs = pd.concat(probs_list)
# In[44]:
probs_tail = probs[probs.Tenor > 360]
gg.ggplot(probs_tail, gg.aes(x='Count Top', weight='Probs True')
) + gg.facet_grid('Tenor') + gg.geom_bar() + gg.geom_step(
gg.aes(y='Probs MLE', color='red')) + gg.geom_step(
gg.aes(y='Probs NN', color='blue')) + gg.scale_x_continuous(
limits=(0, len(count_tops)))
# In[57]:
# KL divergences
kl_df = pd.DataFrame({
'Tenor': range(0, t_end + 1),
'KL MLE': kl_mle_list,
'KL NN': kl_nn_list
})
print kl_df.head()
#! /usr/bin/env/ python
#================== This line is 79 spaces wide ==============================#
import ggplot
test_data = ggplot.mtcars.tail(15)
print test_data
##def average_weight(df, x_value, w_value):
## for x_item in df.x_value.unique():
## for w_item in df.w_value.unique():
## print df[(df.x_value == x_item) & (df.w_value == w_item)].sum()
##average_weight(test_data, 'cyl', 'carb')
p = ggplot.ggplot(ggplot.aes(x = 'factor(cyl)'), data = test_data) +\
ggplot.geom_bar()
## ggplot.facet_grid(x = u'cyl', y = u'gear')
print p
the_max = np.max(model2scores[model][plot_key_name])
the_min = np.min(model2scores[model][plot_key_name])
total = len(model2scores[model][plot_key_name])
for value in model2scores[model][plot_key_name]:
plot_dataset.append(
[model, value, the_mean / total, the_std, the_max, the_min])
plot_dataset_pd = pd.DataFrame(
plot_dataset,
columns=['model', 'value', 'weight', 'std', 'max', 'min'])
if 'logloss' in plot_key_name:
p = ggplot.ggplot(ggplot.aes(x = 'model', fill = 'model', weight = 'weight'), data = plot_dataset_pd) +\
ggplot.geom_bar(position = 'stack', width = 4) +\
ggplot.geom_errorbar(ggplot.aes(x = 'model', y = 'value')) +\
ggplot.ylim(0 ,5.05) +\
ggplot.ggtitle(plot_key_name)
#print(p)
elif 'time' in plot_key_name:
p = ggplot.ggplot(ggplot.aes(x = 'model', fill = 'model', weight = 'weight'), data = plot_dataset_pd) +\
ggplot.geom_bar(position = 'stack', width = 4) +\
ggplot.geom_errorbar(ggplot.aes(x = 'model', y = 'value')) +\
ggplot.ggtitle(plot_key_name)
#print(p)
# For example, select the following lines
x = 7
x**2
# and remember to press COMMAND + ENTER
# You can also run code directly in the console below.
#####################################################################################
# Here is an example of using Rodeo:
# We'll use the popular package called Pandas
# Install it with pip
! pip install pandas
# Import it as 'pd'
import pandas as pd
# Create a dataframe
df=pd.DataFrame({"Animal":["dog","dolphin","chicken","ant","spider"],"Legs":[4,0,2,6,8]})
df.head()
#####################################################################################
# An example of making a plot:
! pip install ggplot
from ggplot import ggplot, aes, geom_bar
ggplot(df, aes(x="Animal", weight="Legs")) + geom_bar(fill='blue')
# Find this tutorial helpful? Checkout the blue sidebar for more tutorials!
