In [58]:
%matplotlib inline
import pandas as pd
import numpy as np
from scipy import stats
from sklearn.ensemble import GradientBoostingClassifier
from sklearn import cross_validation as cv
from sklearn.metrics import accuracy_score
from sklearn.metrics import roc_auc_score
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
import matplotlib.pyplot as plt
import seaborn as sns
In [59]:
slide5 = pd.read_csv('/Users/alex/Projects/AtheyLab/Visualize/BoxAndWhisker/data/Wiley_Slide5_c0_114.csv')
slide6_1 = pd.read_csv('/Users/alex/Projects/AtheyLab/Visualize/BoxAndWhisker/data/Wiley_Slide6_1_c0_114.csv')
slide6_2 = pd.read_csv('/Users/alex/Projects/AtheyLab/Visualize/BoxAndWhisker/data/Wiley_Slide6_2_c0_114.csv')
slide7 = pd.read_csv('/Users/alex/Projects/AtheyLab/Visualize/BoxAndWhisker/data/Wiley_Slide7_c0_114.csv')
slide8 = pd.read_csv('/Users/alex/Projects/AtheyLab/Visualize/BoxAndWhisker/data/Wiley_Slide8_c0_114.csv')
#names = ['Acute Vehicle' 'Acute Cortisol', 'Chronic Vehicle', 'Chronic Cortisol']
names = ['AV' 'AC', 'CV', 'CC']
In [60]:
slide5 = slide5.drop('Case', axis = 1)
slide5.describe()
Out[60]:
In [61]:
print('Slide 6_1: ' + str(slide6_1.shape))
print('Slide 6_2: ' + str(slide6_2.shape))
slide6 = slide6_1.append(slide6_2)
slide6 = slide6.drop('Case', axis = 1)
slide6.describe()
Out[61]:
In [62]:
slide7 = slide7.drop('Case', axis = 1)
slide7.describe()
Out[62]:
In [63]:
slide8 = slide8.drop('Case', axis = 1)
slide8.describe()
Out[63]:
In [64]:
volumes = [slide5['Volume'], slide6['Volume'], slide7['Volume'], slide8['Volume']]
sns.boxplot(volumes, color = "pastel", names = names, label = 'Volume');
In [65]:
for vol in volumes:
vol = vol[~((vol - vol.mean()).abs() > 3 * vol.std())]
print(vol.shape)
sns.boxplot(volumes, color="pastel", names = names, label = 'Volume');
In [54]:
for vol in volumes:
In [ ]: