Commit a8ff27bc authored by François  LAURENT's avatar François LAURENT
Browse files

SciPy course material complete

parent 1dbef0a4
%% Cell type:markdown id:a5a5210d tags:
Import `numpy`, `pandas`, the `pyplot` module from `matplotlib`, `seaborn`, and the `stats` module from `scipy`:
## Q
Import `numpy`, `pandas`, the `pyplot` module from `matplotlib`, `seaborn`, and the `stats` module from `scipy`.
%% Cell type:markdown id:5ac6cc32 tags:
## A
%% Cell type:code id:529c5f56 tags:
``` python
import numpy as np
import pandas as pd
from scipy import stats
from matplotlib import pyplot as plt
import seaborn as sns
```
%% Cell type:markdown id:bb564f37 tags:
%% Cell type:markdown id:93ad4aaf tags:
# Comparison of two group means
%% Cell type:markdown id:0e4fd0d9 tags:
## Q
Load the `mi.csv` data file located in the `data` directory of the course repository.
%% Cell type:markdown id:08c1dd12 tags:
Load the `mi.csv` data file located in the `data` directory of the course repository:
## A
%% Cell type:code id:00130518 tags:
``` python
df = pd.read_csv('../data/mi.csv', index_col=0)
df.head()
```
%%%% Output: execute_result
Age OwnsHouse PhysicalActivity Sex LivesWithPartner LivesWithKids \
1 22.33 Yes 3.0 Female No No
2 28.83 Yes 0.0 Female Yes No
3 23.67 Yes 0.0 Female Yes No
4 21.17 No 0.5 Female No No
5 26.17 Yes 1.5 Female No No
BornInCity Inbreeding BMI CMVPositiveSerology ... \
1 Yes 94.9627 20.13 No ...
2 Yes 79.1024 21.33 Yes ...
3 Yes 117.2540 22.18 No ...
4 No 94.1796 18.68 No ...
5 Yes 105.1250 29.01 No ...
VaccineWhoopingCough VaccineYellowFever VaccineHepB VaccineFlu SUBJID \
1 Yes No Yes No 2
2 Yes No Yes No 3
3 No No Yes No 4
4 No No Yes No 5
5 Yes No Yes No 8
DepressionScore HeartRate Temperature HourOfSampling DayOfSampling
1 0.0 66 36.8 8.883 40
2 0.0 66 37.4 9.350 40
3 0.0 62 36.9 8.667 40
4 1.0 64 36.0 9.883 40
5 0.0 67 36.7 8.550 81
[5 rows x 43 columns]
%% Cell type:markdown id:9cc036b2 tags:
Question: anything missing?
## Q
Anything missing?
%% Cell type:markdown id:99d5dc74 tags:
## A
%% Cell type:code id:8a648a9b tags:
``` python
df.shape
```
%%%% Output: execute_result
(816, 43)
%% Cell type:code id:2f0a8116 tags:
``` python
# in Jupyter-lab, pandas is set to display dataframes with a limited number of columns
pd.options.display.max_columns = None
df.head()
```
%%%% Output: execute_result
Age OwnsHouse PhysicalActivity Sex LivesWithPartner LivesWithKids \
1 22.33 Yes 3.0 Female No No
2 28.83 Yes 0.0 Female Yes No
3 23.67 Yes 0.0 Female Yes No
4 21.17 No 0.5 Female No No
5 26.17 Yes 1.5 Female No No
BornInCity Inbreeding BMI CMVPositiveSerology FluIgG MetabolicScore \
1 Yes 94.9627 20.13 No 0.464319 0
2 Yes 79.1024 21.33 Yes -0.049817 1
3 Yes 117.2540 22.18 No 0.332944 2
4 No 94.1796 18.68 No 0.404886 0
5 Yes 105.1250 29.01 No -0.303782 1
LowAppetite TroubleConcentrating TroubleSleeping HoursOfSleep Listless \
1 0 0 1.0 9.00 3
2 0 0 1.0 7.05 3
3 0 0 1.0 6.50 3
4 0 0 2.0 10.00 3
5 0 0 1.0 9.00 0
UsesCannabis RecentPersonalCrisis Smoking Employed Education \
1 No No Never No PhD
2 No No Active Yes Baccalaureat
3 Yes No Active Yes Baccalaureat
4 No No Never No PhD
5 No No Never Yes Baccalaureat
DustExposure Income HadMeasles HadRubella HadChickenPox HadMumps \
1 No (1000-2000] No No Yes No
2 No (2000-3000] No No Yes No
3 Current (2000-3000] No No Yes No
4 No (3000-inf] No No Yes No
5 No [0-1000] No No No No
HadTonsillectomy HadAppendicectomy VaccineHepA VaccineMMR VaccineTyphoid \
1 No No No No No
2 No No No No No
3 No No No No No
4 No No No No No
5 No No No No No
VaccineWhoopingCough VaccineYellowFever VaccineHepB VaccineFlu SUBJID \
1 Yes No Yes No 2
2 Yes No Yes No 3
3 No No Yes No 4
4 No No Yes No 5
5 Yes No Yes No 8
DepressionScore HeartRate Temperature HourOfSampling DayOfSampling
1 0.0 66 36.8 8.883 40
2 0.0 66 37.4 9.350 40
3 0.0 62 36.9 8.667 40
4 1.0 64 36.0 9.883 40
5 0.0 67 36.7 8.550 81
%% Cell type:markdown id:3512f950 tags:
Show a summary table for these data:
## Q
Show a summary table for these data.
%% Cell type:markdown id:6984434b tags:
## A
%% Cell type:code id:a7a7d087 tags:
``` python
df.describe()
```
%%%% Output: execute_result
Age PhysicalActivity Inbreeding BMI FluIgG \
count 816.000000 816.000000 816.000000 816.000000 816.000000
mean 46.485711 2.751804 91.904255 24.208958 0.203601
std 13.854402 3.565008 12.936172 3.181184 0.232411
min 20.170000 0.000000 43.727000 18.500000 -0.430491
25% 35.830000 0.500000 84.077225 21.770000 0.065082
50% 47.710000 2.000000 91.862800 23.850000 0.227855
75% 58.352500 4.000000 100.008000 26.210000 0.363819
max 69.750000 49.000000 150.107000 32.000000 0.769841
MetabolicScore LowAppetite TroubleConcentrating TroubleSleeping \
count 816.000000 816.000000 816.000000 816.000000
mean 0.932598 0.512255 0.355392 1.119771
std 0.893942 1.674008 1.408535 0.931400
min 0.000000 0.000000 0.000000 0.000000
25% 0.000000 0.000000 0.000000 0.000000
50% 1.000000 0.000000 0.000000 1.000000
75% 1.000000 0.000000 0.000000 2.000000
max 4.000000 14.000000 14.000000 3.000000
HoursOfSleep Listless SUBJID DepressionScore HeartRate \
count 816.000000 816.000000 816.000000 816.000000 816.000000
mean 7.499246 1.290441 576.877451 0.544526 59.209559
std 1.017186 2.055716 518.489935 1.333918 9.206104
min 3.000000 0.000000 2.000000 0.000000 37.000000
25% 7.000000 0.000000 300.750000 0.000000 54.000000
50% 7.500000 0.000000 556.500000 0.000000 58.000000
75% 8.000000 3.000000 779.250000 1.000000 65.000000
max 12.000000 14.000000 5701.000000 14.000000 100.000000
Temperature HourOfSampling DayOfSampling
count 816.000000 816.000000 816.000000
mean 36.431985 9.214806 185.485294
std 0.318461 0.378376 84.971737
min 35.700000 8.433000 17.000000
25% 36.200000 8.917000 136.000000
50% 36.400000 9.233000 187.000000
75% 36.600000 9.550000 263.000000
max 37.700000 11.217000 335.000000
%% Cell type:markdown id:ec2a049f tags:
%% Cell type:markdown id:04163591 tags:
## Q
Inspect the distribution of variables `Age` and `OwnsHouse`.
Inspect the distribution of variables `Age` and `OwnsHouse`:
%% Cell type:markdown id:d6baac23 tags:
%% Cell type:code id:14572a36 tags:
## A
%% Cell type:code id:5de6412d tags:
``` python
# categorical vs continuous => boxplot, violinplot
sns.boxplot(x='OwnsHouse', y='Age', data=df);
# optional
sns.swarmplot(x='OwnsHouse', y='Age', data=df, linewidth=1, size=3);
```
%%%% Output: display_data
![](data:image/png;base64,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)
%% Cell type:code id:9c625646 tags:
%% Cell type:code id:f793503f tags:
``` python
!cowsay "Where on Earth ALL younger people own a house while elder people do not?"
```
%%%% Output: stream
_________________________________________
/ Where on Earth ALL younger people own a \
\ house while elder people do not? /
-----------------------------------------
\ ^__^
\ (oo)\_______
(__)\ )\/\
||----w |
|| ||
%% Cell type:markdown id:af5660e7 tags:
%% Cell type:markdown id:1e94c17b tags:
## Q
Isolate the house-owners group from the others, draw their respective age distributions and check they are normally distributed:
Isolate the house-owners group from the others, draw their respective age distributions and check they are normally distributed.
%% Cell type:code id:86252da3 tags:
%% Cell type:code id:55d18f16 tags:
``` python
group = df.groupby('OwnsHouse').groups
house_owners = group['Yes']
others = group['No']
house_owners_age = df.loc[house_owners, 'Age']
others_age = df.loc[others, 'Age']
```
%% Cell type:code id:1f4abc62 tags:
%% Cell type:code id:3d1a44e6 tags:
``` python
sns.histplot(hue='OwnsHouse', y='Age', data=df, kde=True);
```
%%%% Output: display_data
![](data:image/png;base64,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)
%% Cell type:code id:b67a8ea8 tags:
%% Cell type:code id:ddf5d4b0 tags:
``` python
(theoretical_quantiles, observed_quantiles), (slope, intercept, _) = stats.probplot(house_owners_age, fit=True)
plt.scatter(theoretical_quantiles, observed_quantiles, marker='+', color='b')
plt.axline((0, intercept), slope=slope, color='r');
```
%%%% Output: display_data
![](data:image/png;base64,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)
%% Cell type:markdown id:1d0bb402 tags:
\[CORR\]
%% Cell type:markdown id:24b49c4c tags:
The red line is fitted to the blue points and does not align well on the linear part. To better illustrate what is the linear part, we reimplement the regression (the exact implementation is out of the scope of this session):
%% Cell type:code id:8f971da3 tags:
%% Cell type:code id:0f888c53 tags:
``` python
import statsmodels.api as sm # anticipating the next class...
central = (-1<theoretical_quantiles) & (theoretical_quantiles<1)
model = sm.OLS(observed_quantiles[central], sm.add_constant(theoretical_quantiles[central])).fit()
a, b = model.params
plt.scatter(theoretical_quantiles, observed_quantiles, marker='+', color='b')
plt.axline((0, a), slope=b, color='r');
```
%%%% Output: display_data
![](data:image/png;base64,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)
%% Cell type:markdown id:b8ecfebf tags:
\[CORR\]
%% Cell type:markdown id:f35584b7 tags:
The misalignment of the default regression line on the central part of the distribution is indicative of some asymmetry, while the diverging tails also hint at some departure from normality (kurtosis).
The misalignment of the default regression line on the central part of the distribution is indicative of some asymmetry, while the diverging tails also hint at some departure from normality (kurtosis). The sampling procedure clearly excluded people younger than 20 years old or elder than 70, which results in truncated distributions.
Here, we have comfortable sample sizes and these departures from normality may not affect the power of the statistical test.
%% Cell type:markdown id:f6de8e66 tags:
%% Cell type:markdown id:2cc80be1 tags:
## Q
Are the sample size and variance of the two groups similar enough for running a standard $t$ test?
%% Cell type:code id:d5ac4dc5 tags:
%% Cell type:markdown id:cd58c73a tags:
## A
%% Cell type:code id:0dbb79f7 tags:
``` python
len(house_owners_age), len(others_age), np.var(house_owners_age), np.var(others_age)
len(house_owners_age), len(others_age), np.std(house_owners_age), np.std(others_age)
```
%%%% Output: execute_result
(288, 528, 219.94736689332564, 138.81976459481174)
(288, 528, 14.830622606395378, 11.782179959362857)
%% Cell type:markdown id:e177b52b tags:
%% Cell type:markdown id:3e221ea2 tags:
\[CORR\] `ttest_ind` allows variance ratios up to $2$. The groups can have different sample sizes.
`ttest_ind` allows standard deviation ratios [up to $2$](https://en.wikipedia.org/wiki/Student%27s_t-test#Equal_or_unequal_sample_sizes,_similar_variances_(1/2_%3C_sX1/sX2_%3C_2)). The groups can have different sample sizes.
%% Cell type:markdown id:cd273f22 tags:
%% Cell type:markdown id:d61f454a tags:
Test the group mean ages equal:
## Q
%% Cell type:code id:ed503837 tags:
Test the group mean ages equal.
%% Cell type:markdown id:b076e8e6 tags:
## A
%% Cell type:code id:1d238900 tags:
``` python
# define your significance level first!
significance_level = 0.05
# run a t-test for independent samples
stats.ttest_ind(house_owners_age, others_age)
```
%%%% Output: execute_result
Ttest_indResult(statistic=-10.858676761684935, pvalue=9.562420864768222e-26)
%% Cell type:markdown id:967b1f9f tags:
%% Cell type:markdown id:62b30b76 tags:
## Q
How would you report the result of this test?
%% Cell type:code id:de90c6e8 tags:
%% Cell type:markdown id:efeac3ab tags:
## A
%% Cell type:code id:341157b6 tags:
``` python
# we need:
# * the number of degrees of freedom, to give a complete report of the outcome of the t-test,
n1, n2 = len(house_owners_age), len(others_age)
degrees_of_freedom = n1 + n2 - 2
# * the mean difference (this is almost an effect size in itself, an intuitive one),
# * the mean difference (this is almost an effect size, not compared with the associated variability),
mean_difference = np.mean(house_owners_age) - np.mean(others_age)
# * and the effect size.
f, _ = stats.ttest_ind(house_owners_age, others_age)
cohen_d = f * np.sqrt(1/n1 + 1/n2)
t, _ = stats.ttest_ind(house_owners_age, others_age)
cohen_d = t * np.sqrt(1/n1 + 1/n2)
degrees_of_freedom, mean_difference, cohen_d
# alternatively:
import pingouin as pg
unbiased_cohen_d = pg.compute_effsize(house_owners_age, others_age)
degrees_of_freedom, mean_difference, cohen_d, unbiased_cohen_d
```
%%%% Output: execute_result
(814, -10.305953282828284, -0.7954424784394866)
%% Cell type:markdown id:21e69d05 tags:
(814, -10.305953282828284, -0.7954424784394866, -0.7954424784394866)
\[CORR\]
%% Cell type:markdown id:b79f8a5c tags:
«**In our study**, house owners ($n=288$) were found to be significantly younger than the other surveyed people ($n=528$; $10.3$ years younger on average, $t(814)=-10.9$, $p<0.05$). This effect was found to be large (Cohen's $d \approx 0.8$).»
Note: as we report the sample size for each group, we may omit the (still nice-to-have) information of the number of degrees of freedom.
%% Cell type:markdown id:54db26df tags:
%% Cell type:markdown id:f72698b7 tags:
## Q
\[optional; good for playing with Python rather than statistical methods\]
Although tractable in principle, the group difference in variance is quite large and -- had we smaller samples -- we could instead use the Welch's $t$ test that is known to better control for type-1 errors in cases of differing variances, but also a slightly lower power.
As it is now clear we have a relationship between age and owning a house, let us compute the rejection rate (or power) as a function of sample size.
Proposal:
* loop over decreasing sample sizes (*e.g.* 200, 50, 20, 10, 5),
* randomly pick a subsample of that size from each group,
* compare their means using the standard Student $t$-test and Welch $t$-test,
* observe whether each test successfully rejects $H_0$ for a constant significance level (*e.g.* 5%),
* replicate this procedure many times (*e.g.* 100)
* and compute the rejection rate for each sample size and type of test.
%% Cell type:markdown id:8a2bc253 tags:
## Help: subsampling
%% Cell type:code id:fd050fbc tags:
``` python
# let us consider an example sample
sample = others_age
# and a subsample size
n = 200
# we need a random generator
rng = np.random.default_rng()
# now we can pick n observations from the original sample
# calling the `choice` method of the random generator
subsample = rng.choice(sample, n)
# in principle the smaller sample will exhibit similar
# properties as the original sample; both are drawn from
# the population in similar ways
bins = np.arange(20, 70+1, 5)
sns.histplot(sample, bins=bins)
sns.histplot(subsample, bins=bins);
```
%%%% Output: display_data
![](data:image/png;base64,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)
%% Cell type:markdown id:b44a7b2b tags:
## A
%% Cell type:code id:35541f89 tags:
``` python
significance_level = 0.05
sample1 = house_owners_age
sample2 = others_age
sample_size = min(len(sample1), len(sample2))
```
%% Cell type:code id:2ae175e5 tags:
``` python
from collections import defaultdict
sample_sizes = []
test_types = []
rejection_rates = []
rng = np.random.default_rng()
for relative_sample_size in (1, .2, .1, .05, .025):
n = int(relative_sample_size * sample_size)
nreplicates = 100
rejections = defaultdict(lambda: 0)
for _ in range(nreplicates):
subsample1 = rng.choice(sample1, n)
subsample2 = rng.choice(sample2, n)
for test_type in ('Student', 'Welch'):
t, pv = stats.ttest_ind(subsample1, subsample2, equal_var=test_type=='Student')
if pv <= significance_level:
rejections[test_type] = rejections[test_type] + 1
for test_type in rejections:
rejection_rates.append(rejections[test_type] / nreplicates)
sample_sizes.append(n)
test_types.append(test_type)
result = pd.DataFrame({'sample size': sample_sizes, 'test': test_types, 'power': rejection_rates})
```