jcheong0428

jcheong0428

# This sets the pdf font type so that it imports correctly in Adobe Illustrator. 
# Source: http://jonathansoma.com/lede/data-studio/matplotlib/exporting-from-matplotlib-to-open-in-adobe-illustrator/
import matplotlib
matplotlib.rcParams['pdf.fonttype'] = 42
matplotlib.rcParams['ps.fonttype'] = 42

# Generating 2x retina plots 
%config InlineBackend.figure_format = 'retina'

# Set base figure size 

jcheong0428

import numpy as np
import pandas as pd
def parse_triangle(df, condition='upper'):
    '''
    This function grabs the upper triangle of a correlation matrix
    by masking out the bottom triangle (tril) and returns the values. 
    You can use scipy.spatial.distance.squareform to recreate matrix from upper triangle
    
    Args:
      df: pandas or numpy correlation matrix

jcheong0428

# First load rpy2 
%load_ext rpy2.ipython

# Then load packages in a separate cell
%%R
require('lme4')
require('lmerTest')
require('lattice')
require('boot')
require('sjPlot')

jcheong0428

# Correct p-value by adjusting degrees of freedom.
# Degrees of freedom is divided by two and then looked up 
# Reference:
# https://www.ncbi.nlm.nih.gov/pubmed/27751943
# Chen, G., Taylor, P. A., Shin, Y. W., Reynolds, R. C., & Cox, R. W. (2017). Untangling the relatedness among correlations, Part II: Inter-subject correlation group analysis through linear mixed-effects modeling. Neuroimage, 147, 825-840.

from scipy.stats import t
tt = 9.83
df = 17.6/2.
pval = t.sf(np.abs(tt), df)*2 

jcheong0428

jcheong0428

def crosscorr(datax, datay, lag=0):
    """ Lag-N cross correlation. 
    Calculates cross correlations using pandas functionality that can be used in a list comprehension. 
    
    Parameters
    ----------
    lag : int, default 0
    datax, datay : pandas.Series objects of equal length

    Returns

jcheong0428

import pandas as pd
import numpy as np
%matplotlib inline
import matplotlib.pyplot as plt
import seaborn as sns
import scipy.stats as stats

df = pd.read_csv('synchrony_sample.csv')
overall_pearson_r = df.corr().iloc[0,1]
print(f"Pandas computed Pearson r: {overall_pearson_r}")

jcheong0428

# Set window size to compute moving window synchrony.
r_window_size = 120
# Interpolate missing data.
df_interpolated = df.interpolate()
# Compute rolling window synchrony
rolling_r = df_interpolated['S1_Joy'].rolling(window=r_window_size, center=True).corr(df_interpolated['S2_Joy'])
f,ax=plt.subplots(2,1,figsize=(14,6),sharex=True)
df.rolling(window=30,center=True).median().plot(ax=ax[0])
ax[0].set(xlabel='Frame',ylabel='Smiling Evidence')
rolling_r.plot(ax=ax[1])

jcheong0428

def crosscorr(datax, datay, lag=0, wrap=False):
    """ Lag-N cross correlation. 
    Shifted data filled with NaNs 
    
    Parameters
    ----------
    lag : int, default 0
    datax, datay : pandas.Series objects of equal length

    Returns