def make_figures(firsts, others):
"""Plot Pmfs of pregnancy length.
firsts: DataFrame
others: DataFrame
"""
# plot the PMFs
first_pmf = thinkstats2.Pmf(firsts.prglngth, label='first')
other_pmf = thinkstats2.Pmf(others.prglngth, label='other')
width = 0.45
thinkplot.PrePlot(2, cols=2)
thinkplot.Hist(first_pmf, align='right', width=width)
thinkplot.Hist(other_pmf, align='left', width=width)
thinkplot.Config(xlabel='weeks',
ylabel='probability',
axis=[27, 46, 0, 0.6])
thinkplot.PrePlot(2)
thinkplot.SubPlot(2)
thinkplot.Pmfs([first_pmf, other_pmf])
thinkplot.Save(root='probability_nsfg_pmf',
xlabel='weeks',
axis=[27, 46, 0, 0.6])
# plot the differences in the PMFs
weeks = range(35, 46)
diffs = []
for week in weeks:
p1 = first_pmf.Prob(week)
p2 = other_pmf.Prob(week)
diff = 100 * (p1 - p2)
diffs.append(diff)
thinkplot.Bar(weeks, diffs)
thinkplot.Save(root='probability_nsfg_diffs',
title='Difference in PMFs',
xlabel='weeks',
ylabel='percentage points',
legend=False)
def main():
results = ReadResults()
speeds = GetSpeeds(results)
# speeds = BinData(speeds, 3, 12, 100)
pmf = thinkstats2.MakePmfFromList(speeds, 'speeds')
thinkplot.Hist(pmf)
thinkplot.Show(title='PMF of running speed',
xlabel='speed (mph)',
ylabel='probability')
def MakeHists(male, female):
"""Plot Hists for live births
live: DataFrame
others: DataFrame
"""
thinkplot.PrePlot(rows=1, cols=2)
hist = thinkstats2.Hist(male.alcwknd)
thinkplot.SubPlot(1)
thinkplot.Config(axis=[0, 800, 0, 600],
ylabel='Number of people',
xlabel='Alcohol consumed (grams)',
title='Weekend Alcohol Consumption for Men')
thinkplot.Hist(hist, alpha=1)
hist = thinkstats2.Hist(female.alcwknd)
thinkplot.SubPlot(2)
thinkplot.Config(axis=[0, 800, 0, 1200],
ylabel='Number of people',
xlabel='Alcohol consumed (grams)',
title='Weekend Alcohol Consumption for Women')
thinkplot.Hist(hist, alpha=1)
thinkplot.Show()
def Estimate4(lam=2, m=1000000):
estimates = []
for i in range(m):
L = SimulateGame(lam)
estimates.append(L)
print('Experiment 4')
print('rmse L', RMSE(estimates, lam))
print('mean error L', MeanError(estimates, lam))
pmf = thinkstats2.Pmf(estimates)
thinkplot.Hist(pmf)
thinkplot.Show()
def main():
results = ReadResults()
speeds = GetSpeeds(results)
#speeds = BinData(speeds, 3, 12, 25)
pmf = thinkstats2.MakePmfFromList(speeds, 'speeds')
mean = pmf.Mean()
var = pmf.Var()
print 'mean=',mean
print 'var=',var
thinkplot.Hist(pmf)
thinkplot.Show(title='PMF of running speed',
xlabel='speed (mph)',
ylabel='probability')
def PairWiseDifferences(live):
live = live[live.prglngth >= 37]
preg_map = nsfg.MakePregMap(live)
diffs = []
for caseid, indices in preg_map.items():
lengths = live.loc[indices].prglngth.values
if len(lengths) >= 2:
diffs.extend(Diffs(lengths))
mean = thinkstats2.Mean(diffs)
print('Mean difference between pairs', mean)
pmf = thinkstats2.Pmf(diffs)
thinkplot.Hist(pmf, align='center')
thinkplot.Show(xlabel='Difference in weeks', ylabel='PMF')
def PredRemaining(self, rem_time, score):
"""Plots the predictive distribution for final number of goals.
rem_time: remaining time in the game in minutes
score: number of goals already scored
"""
metapmf = thinkbayes2.Pmf()
for lam, prob in self.Items():
lt = lam * rem_time / 90
pred = thinkbayes2.MakePoissonPmf(lt, 15)
metapmf[pred] = prob
#thinkplot.Pdf(pred, color='gray', alpha=0.1, linewidth=0.5)
mix = thinkbayes2.MakeMixture(metapmf)
mix += score
thinkplot.Hist(mix)
thinkplot.Show()
def MakeHists(live):
"""Plot Hists for live births
live: DataFrame
others: DataFrame
"""
hist = thinkstats2.Hist(np.floor(live.agepreg), label='agepreg')
thinkplot.PrePlot(2, cols=2)
thinkplot.SubPlot(1)
thinkplot.Hist(hist)
thinkplot.Config(xlabel='years', ylabel='frequency', axis=[0, 45, 0, 700])
thinkplot.SubPlot(2)
thinkplot.Pmf(hist)
thinkplot.Save(root='probability_agepreg_hist',
xlabel='years',
axis=[0, 45, 0, 700])
def PrintExtremes(live):
"""Plots the histogram of pregnancy lengths and prints the extremes.
live: DataFrame of live births
"""
hist = statFunctions.Hist(live.prglngth)
thinkplot.Hist(hist, label='live births')
thinkplot.Save(root='first_nsfg_hist_live',
title='Histogram',
xlabel='weeks',
ylabel='frequency')
print('Shortest lengths:')
for weeks, freq in hist.Smallest(10):
print(weeks, freq)
print('Longest lengths:')
for weeks, freq in hist.Largest(10):
print(weeks, freq)
def PairWiseDifferences(live):
"""Summarize pairwise differences for children of the same mother.
live: DataFrame of pregnancy records for live births
"""
live = live[live.prglngth >= 37]
preg_map = nsfg.MakePregMap(live)
diffs = []
for caseid, indices in preg_map.items():
lengths = live.loc[indices].prglngth.values
if len(lengths) >= 2:
diffs.extend(Diffs(lengths))
mean = thinkstats2.Mean(diffs)
print('Mean difference between pairs', mean)
pmf = thinkstats2.Pmf(diffs)
thinkplot.Hist(pmf, align='center')
thinkplot.Show(xlabel='Difference in weeks', ylabel='PMF')
def main():
'''initializes an instance of a learning styles probability distribution
updates the probability distribution based on data
checks the strength of the evidence that the distribution in hacker school is substantiallly different'''
sensing_data = (2, 0)
sensing_hypo = 50
sensing_ratio = 65
sensing_dist = StyleDist(range(0, 101))
sensing_likelihood = sensing_dist.Likelihood(sensing_data, sensing_hypo)
print('p(D|50%)', sensing_likelihood)
thinkplot.Hist(sensing_dist)
#set p(D|~H)
b_uniform = StyleDist(range(0, 101))
b_uniform.Remove(sensing_ratio)
b_uniform.Normalize()
# %matplotlib inline
thinkplot.Pmf(sensing_dist)
return sensing_dist
def main():
results = relay.ReadResults()
speeds = relay.GetSpeeds(results)
# plot the distribution of actual speeds
pmf = thinkstats2.MakePmfFromList(speeds, 'actual speeds')
# plot the biased distribution seen by the observer
biased = BiasPmf(pmf, 7.5, name='observed speeds')
thinkplot.Hist(biased)
thinkplot.Save(root='observed_speeds',
title='PMF of running speed',
xlabel='speed (mph)',
ylabel='probability')
cdf = thinkstats2.MakeCdfFromPmf(biased)
thinkplot.Clf()
thinkplot.Cdf(cdf)
thinkplot.Save(root='observed_speeds_cdf',
title='CDF of running speed',
xlabel='speed (mph)',
ylabel='cumulative probability')
runs_mean = runs.mean()# the mean of the runs runs_std = runs.std() # the standard deviation of the runs print (runs_mean) print (runs_std) # In[27]: # Building the histograms of both the wins and the runs wins_hist = thinkstats2.Hist(wins, label='Wins') runs_hist = thinkstats2.Hist(runs, label='Runs Scored') width = 0.45 thinkplot.PrePlot(2, cols=2) thinkplot.Hist(wins_hist, align='right', width=width) thinkplot.Hist(runs_hist, align='left', width=width) thinkplot.Config(xlabel='Result', ylabel='Probability') # In[29]: # Building the PMFs of both the wins and the runs wins_pmf = thinkstats2.Pmf(wins, label='Wins') runs_pmf = thinkstats2.Pmf(runs, label='Runs') width=0.45 thinkplot.PrePlot(2, cols=2) thinkplot.Hist(wins_pmf, align='right', width=width) thinkplot.Hist(runs_pmf, align='left', width=width) thinkplot.Config(xlabel='Result', ylabel='PMF')
import thinkstats2 as ts import thinkplot as tp seq = [1,0,2,7,2,0,9,11,10,9,4,5,3,4,2,2,2] h = ts.Hist(seq) tp.Hist(h) tp.Show()
def main():
pmf_dice = thinkbayes.Pmf()
pmf_dice.Set(Die(4), 5)
pmf_dice.Set(Die(6), 4)
pmf_dice.Set(Die(8), 3)
pmf_dice.Set(Die(12), 2)
pmf_dice.Set(Die(20), 1)
pmf_dice.Normalize()
mix = thinkbayes.Pmf()
for die, weight in pmf_dice.Items():
for outcome, prob in die.Items():
mix.Incr(outcome, weight * prob)
mix = thinkbayes.MakeMixture(pmf_dice)
colors = thinkplot.Brewer.Colors()
thinkplot.Hist(mix, width=0.9, color=colors[4])
thinkplot.Save(root='dungeons3',
xlabel='Outcome',
ylabel='Probability',
formats=FORMATS)
random.seed(17)
d6 = Die(6, 'd6')
dice = [d6] * 3
three = thinkbayes.SampleSum(dice, 1000)
three.name = 'sample'
three.Print()
three_exact = d6 + d6 + d6
three_exact.name = 'exact'
three_exact.Print()
thinkplot.PrePlot(num=2)
thinkplot.Pmf(three)
thinkplot.Pmf(three_exact, linestyle='dashed')
thinkplot.Save(root='dungeons1',
xlabel='Sum of three d6',
ylabel='Probability',
axis=[2, 19, 0, 0.15],
formats=FORMATS)
thinkplot.Clf()
thinkplot.PrePlot(num=1)
# compute the distribution of the best attribute the hard way
# best_attr2 = PmfMax(three_exact, three_exact)
# best_attr4 = PmfMax(best_attr2, best_attr2)
# best_attr6 = PmfMax(best_attr4, best_attr2)
# thinkplot.Pmf(best_attr6)
# and the easy way
best_attr_cdf = three_exact.Max(6)
best_attr_cdf.name = ''
best_attr_pmf = thinkbayes.MakePmfFromCdf(best_attr_cdf)
best_attr_pmf.Print()
thinkplot.Pmf(best_attr_pmf)
thinkplot.Save(root='dungeons2',
xlabel='Sum of three d6',
ylabel='Probability',
axis=[2, 19, 0, 0.23],
formats=FORMATS)
import thinkstats2 import thinkplot flfindistdfpmf = thinkstats2.Pmf(flfindistdf['TOTALREV'], label='FLORIDA') vfindistdfpmf = thinkstats2.Pmf(vfindistdf['TOTALREV'], label='VERMONT') # In[53]: width=200000 axis = [0, 800, 0, 0.0005] thinkplot.PrePlot(2, cols =2) thinkplot.Hist(flfindistdfpmf, align = 'right', width = width) thinkplot.Hist(vfindistdfpmf, align = 'left', width = width) thinkplot.Config(xlabel = 'Total Revenue', ylabel = 'PMF') # In[54]: thinkplot.Pmf(flfindistdfpmf) thinkplot.Pmf(vfindistdfpmf) # In[55]:
preg = nsfg.ReadFemPreg() live = preg[preg.outcome == 1] # %% # 第1子と第2子以降に分ける tmp = live.copy() tmp.loc[tmp.prglngth <= 27] = np.nan tmp.loc[tmp.prglngth > 47] = np.nan firsts = tmp[tmp.birthord == 1] others = tmp[tmp.birthord != 1] first_pmf = thinkstats2.Pmf(firsts.prglngth) others_pmf = thinkstats2.Pmf(others.prglngth) # %% # 棒グラフ表示 width = 0.45 thinkplot.PrePlot(2, cols=2) thinkplot.Hist(first_pmf, align='right', width=width) thinkplot.Hist(others_pmf, align='left', width=width) thinkplot.Config(xlabl='week', ylabel='probability', axis=[27, 46, 0, 0.6]) thinkplot.show() # %% # ステップ関数表示 thinkplot.PrePlot(2) thinkplot.Pmfs([first_pmf, others_pmf]) thinkplot.show(xlabl='week', ylabel='probability', axis=[27, 46, 0, 0.6]) # %% [markdown] # ## 3.3 その他の可視化 # %% # 差を棒グラフで表示 weeks = range(35, 46) diffs = [] for week in weeks:
finalmathgrade = map(
int, finalmathgrade) # convert a list of strings to lisdt of integers
# histogram
hist1 = thinkstats2.Hist(Mothereducation)
print(hist1)
hist2 = thinkstats2.Hist(sorted(absences))
print(sorted(absences))
print(hist2)
hist3 = thinkstats2.Hist(familyrelationships)
print(hist3)
hist4 = thinkstats2.Hist(finalmathgrade)
print(hist4)
# plot histogram
thinkplot.Hist(hist1)
thinkplot.Show(xlabel="Mother's education",
ylabel="Frequency",
main="Mother's education")
thinkplot.Hist(hist2)
thinkplot.Show(xlabel="absences",
ylabel="Frequency",
main="Number of days that the student was absent")
thinkplot.Hist(hist3)
thinkplot.Show(xlabel="family relationships",
ylabel="Frequency",
main="quality of family relationships")
thinkplot.Hist(hist4)
# compute the PMF of line estimates (or load the cached version)
if os.path.isfile(pmf_pickle_path):
records_pmf = load_pmf()
else:
records_pmf = create_pmf_from_csv(csv_path)
dates, records = dataframe_to_lists(records_pmf.dataframe)
# compute the marginal distributions for alpha, beta, and sigma.
# save their maximum likelihoods
maximum_likelihoods = [0, 0, 0]
for title, i in [('alpha', 0), ('beta', 1), ('sigma', 2)]:
marginal = records_pmf.Marginal(i)
maximum_likelihoods[i] = marginal.MaximumLikelihood()
thinkplot.Hist(marginal)
plt.title("PMF for " + title)
plt.show()
# compare the alpha and beta maximum likelihoods to the least squares estimate
compare_to_least_squares(maximum_likelihoods[0], maximum_likelihoods[1], dates, records)
# run a monte-carlo simulation of running records (or load the cached version)
date_range = pd.date_range(start=dates[-1], end='1/1/2060', freq='365D')
if os.path.isfile(simulation_pickle_path):
simulated_records = load_simulations()
else:
simulated_records = []
for i in range(1000):
alpha, beta, sigma = records_pmf.Random()
df['Sex'].replace('Unknown', np.nan, inplace=True)
df.dropna(subset=['Sex'], inplace=True)
df['Race'].replace('', np.nan, inplace=True)
df['Race'].replace('Unknown', np.nan, inplace=True)
df['Race'].replace('Other', np.nan, inplace=True)
df.dropna(subset=['Race'], inplace=True)
df['Drug'].replace('', np.nan, inplace=True)
df['Drug'].replace('Unknown', np.nan, inplace=True)
df.dropna(subset=['Drug'], inplace=True)
#change data types
df['Year'] = df['Year'].astype(int)
df['Age'] = df['Age'].astype(int)
#create histograms and report characterisitics
histYear = thinkstats2.Hist(df.Year)
thinkplot.Hist(histYear)
print("mean is", df.Year.mean())
print("mode is", max(df.Year.mode()))
print("variance is", df.Year.var())
print("standard deviation is", df.Year.std())
histAge = thinkstats2.Hist(df.Age)
thinkplot.Hist(histAge, width=1)
print("mean is", df.Age.mean())
print("mode is", max(df.Age.mode()))
print("variance is", df.Age.var())
print("standard deviation is", df.Age.std())
histSex = thinkstats2.Hist(df.Sex)
thinkplot.Hist(histSex)
histRace = thinkstats2.Hist(df.Race)
thinkplot.Hist(histRace)
histDrug = thinkstats2.Hist(df.Drug)
def testHist(self):
hist = thinkstats2.Hist(['red', 'green', 'blue'])
hist['red'] += 1
print(hist)
thinkplot.Hist(hist, width=1)
thinkplot.Show()
plt.hist(pollution_df.COAQI, color='grey')
plt.axvline(CO_mean, color='red', label='Mean')
plt.axvline(CO_mode[0], color='green', label='Mode')
plt.xlabel('CO AQI')
plt.ylabel('Frequency')
plt.show()
print('The CO mean is:', CO_mean)
print('The CO mode is:', CO_mode)
#PMF
#creating a variable for PMF of NO2 AQI & SO2 AQI
no2_pmf = thinkstats2.Pmf(grp_pollution_df['NO2AQI'])
so2_pmf = thinkstats2.Pmf(grp_pollution_df['SO2AQI'])
thinkplot.PrePlot(2, cols=2)
thinkplot.Hist(no2_pmf, label='NO2', align='right', width=0.75)
thinkplot.Hist(so2_pmf, label='SO2', align='left', width=0.75)
thinkplot.Show(xlabel='Parts per Billion',
ylabel='Probability',
axis=[0, 80, 0, 0.10])
#creating the CDF of O3 AQI
t = (grp_pollution_df['O3AQI'])
cdf = thinkstats2.Cdf(t, label='O3')
thinkplot.Clf()
thinkplot.Cdf(cdf)
thinkplot.Show(xlabel='Parts per Million', ylabel='CDF')
#plotting a complementary CDF (CCDF) of O3
thinkplot.Cdf(cdf, complement=True)
thinkplot.Show(xlabel='minutes', ylabel='CCDF', yscale='log')
import nsfg import thinkplot import thinkstats2 pres = nsfg.ReadFemResp() preshist = thinkstats2.Hist(pres) age = thinkstats2.Hist(pres.fmar1age) print(sorted(age.Values())) thinkplot.Hist(age) thinkplot.Show(xlabel='age', ylabel='frequency') marriagenum = thinkstats2.Hist(pres.fmarno) print(sorted(marriagenum.Values())) thinkplot.Hist(marriagenum) thinkplot.Show(xlabel='mariages #', ylabel='frequency') income = thinkstats2.Hist(pres.totincr) print(sorted(income.Values())) thinkplot.Hist(income) thinkplot.Show(xlabel='income', ylabel='frequency') width = 0.30 neverMarried = pres[pres.fmarno == 0] Married = pres[pres.fmarno != 0] never = thinkstats2.Hist(neverMarried.totincr, label="Never Married") married = thinkstats2.Hist(Married.totincr, label="Married")
import thinkplot
import thinkstats2
pres = nsfg.ReadFemResp()
# EX 1
fmar1age = pres['fmar1age']
his = thinkstats2.Hist(pres.fmar1age)
hist1 = thinkstats2.Hist(his)
pres.fmar1age.value_counts().sort_index()
# In[17]:
thinkplot.Hist(hist1, width=0.5)
thinkplot.Show(xlabel='Age at first marriage',
ylabel='Frequency of first marriage')
# In[21]:
# EX 2
fmarno = pres['fmarno']
histo = thinkstats2.Hist(fmarno)
pres.fmarno.value_counts().sort_index()
# In[22]:
thinkplot.Hist(histo,
color='blue',
# Author: Matt Xiao # Data frame from ThinkStats import nsfg import thinkstats2 import thinkplot df = nsfg.ReadFemPreg() hist = thinkstats2.Hist([1, 2, 2, 3, 5]) thinkplot.Hist(hist) thinkplot.Show(xlabel='value', ylabel='frequency')
print(totalPlayed)
#total notplayed:
print(totalDNP)
# In[46]:
hist = thinkstats2.Hist({
1.0: totalPlayed,
0.0: totalDNP
},
label='All-star game')
# In[48]:
thinkplot.Hist(hist)
thinkplot.Config(xlabel='All-star game played',
ylabel='Total amount of players')
# In[49]:
#This i my histogram, as you can see total played players are way much more than those who didn't played in both leagues
#all star game.
# In[50]:
#now back into my question, which league has more players played in its own allstar game.
# In[55]:
hist = thinkstats2.Hist({
for val in sorted(hist.Values()):
print(val, hist.Freq(val))
# In[277]:
for val, freq in hist.Items():
print(val, freq)
# In[278]:
import thinkplot
thinkplot.Hist(hist)
thinkplot.Show(xlabel='value', ylabel='frequency')
# In[279]:
preg = nsfg.ReadFemPreg()
live = preg[preg.outcome == 1]
# In[280]:
hist = thinkstats2.Hist(live.birthwgt_lb, label='birthwgt_lb')
thinkplot.Hist(hist)
import nsfg
import thinkstats2
import thinkplot
#chapter 1 code examples
df = nsfg.ReadFemPreg()
#print(df)
#df = nsfg.CleanFemPreg(df) how to make it work it is already cleaned ??
print(df.outcome.value_counts(sort=False))
print(df['birthwgt_lb'].value_counts(sort=False))
#chapter 2 code examples
myhist = thinkstats2.Hist([1, 2, 2, 3, 5])
print(myhist.Freq(2))
print(myhist.Values())
for val in sorted(myhist.Values()):
print(val, myhist.Freq(val))
thinkplot.Hist(myhist)
thinkplot.Show(xlabel='value', ylabel='frequency', title='Anju')
# remove first element
famList = famList[1:]
romanList = romanList[1:]
# calculate percentage of family size have three or less family members
famLE3 = famList.count("LE3") / float(len(famList))
print('family has three or less members percentage=', "{:.2f}".format(famLE3))
# calculate student in relationship percentage
romanticY = romanList.count("yes") / float(len(romanList))
print('student in relationship percentage=', "{:.2f}".format(romanticY))
famSizeHist = thinkstats2.Hist(famList, label='famsize')
romanList = thinkstats2.Hist(romanList, label='romantic')
# plot familiy size histogram
thinkplot.Hist(famSizeHist)
thinkplot.Show(xlabel='Value', ylabel='Frequency', title='Family Size Fig')
# plot romantic interest histogram
thinkplot.Hist(romanList)
thinkplot.Show(xlabel='Value',
ylabel='Frequency',
title='Romantic Interest Fig')
# Use One Sample T Test to valuate whether this data set is a good sample or not.
# Our null hypothesis is that: true_mu = 0
famList = map(lambda x: 1 if x == 'GT3' else 0, famList)
romanList = map(lambda x: 1 if x == 'yes' else 0, romanList)
true_mu = 0
print('family size: t-statistic = %6.3f pvalue = %6.4f' %
stats.ttest_1samp(famList, true_mu))
# 2. random number generator by math
import math
def drBRandom(lastNum):
return math.cos(lastNum)
rand2List = []
ln = 0.01
for x in range(1, 10):
ln = drBRandom(ln)
rand2List.append(round(ln * 10))
# print(rand2List)
# make list into Pmf
rand1Pmf = thinkstats2.Pmf(rand1List)
rand2Pmf = thinkstats2.Pmf(rand2List)
# print(rand2Pmf)
# Ploting random number PMF
thinkplot.Hist(rand1Pmf)
thinkplot.Show(xlabel='random number',
ylabel='Frequency',
title='Random number1 fig')
thinkplot.Hist(rand2Pmf)
thinkplot.Show(xlabel='random number',
ylabel='Frequency',
title='Random number2 fig')