def do_anovas(some_df, variable):
'''
This method takes a dataframe, returns the pyvttbl
anova object for that element
'''
pyv_df = DataFrame()
if variable == 'qp':
pyv_df['qual'] = str_list(some_df['qualification_performance'])
pyv_df['vals'] = int_list(some_df['adj_diffs'])
elif variable == 'ed':
pyv_df['qual'] = str_list(some_df['education_level'])
pyv_df['vals'] = int_list(some_df['adj_diffs'])
elif variable == 'fp':
pyv_df['qual'] = str_list(some_df['fps'])
pyv_df['vals'] = int_list(some_df['adj_diffs'])
else:
return None
anova = pyv_df.anova1way('vals', 'qual')
anova['omega-sq'] = get_w(anova)
return anova
def test2(self):
R = """Anova: Single Factor on SUPPRESSION
SUMMARY
Groups Count Sum Average Variance
==============================================
AA 128 2048 16 148.792
AB 128 2510.600 19.614 250.326
LAB 128 2945.000 23.008 264.699
O'BRIEN TEST FOR HOMOGENEITY OF VARIANCE
Source of Variation SS df MS F P-value eta^2 Obs. power
============================================================================================
Treatments 1021873.960 2 510936.980 5.229 0.006 0.027 0.823
Error 37227154.824 381 97709.068
============================================================================================
Total 38249028.783 383
ANOVA
Source of Variation SS df MS F P-value eta^2 Obs. power
=========================================================================================
Treatments 3144.039 2 1572.020 7.104 9.348e-04 0.036 0.922
Error 84304.687 381 221.272
=========================================================================================
Total 87448.726 383
POSTHOC MULTIPLE COMPARISONS
Tukey HSD: Table of q-statistics
AA AB LAB
==============================
AA 0 2.749 ns 5.330 **
AB 0 2.581 ns
LAB 0
==============================
+ p < .10 (q-critical[3, 381] = 2.91125483514)
* p < .05 (q-critical[3, 381] = 3.32766157576)
** p < .01 (q-critical[3, 381] = 4.14515568451)"""
df = DataFrame()
df.read_tbl('data/suppression~subjectXgroupXageXcycleXphase.csv')
D = df.anova1way('SUPPRESSION', 'GROUP')
self.assertEqual(str(D), R)
def test2(self):
R="""Anova: Single Factor on SUPPRESSION
SUMMARY
Groups Count Sum Average Variance
==============================================
AA 128 2048 16 148.792
AB 128 2510.600 19.614 250.326
LAB 128 2945.000 23.008 264.699
O'BRIEN TEST FOR HOMOGENEITY OF VARIANCE
Source of Variation SS df MS F P-value eta^2 Obs. power
============================================================================================
Treatments 1021873.960 2 510936.980 5.229 0.006 0.027 0.823
Error 37227154.824 381 97709.068
============================================================================================
Total 38249028.783 383
ANOVA
Source of Variation SS df MS F P-value eta^2 Obs. power
=========================================================================================
Treatments 3144.039 2 1572.020 7.104 9.348e-04 0.036 0.922
Error 84304.687 381 221.272
=========================================================================================
Total 87448.726 383
POSTHOC MULTIPLE COMPARISONS
Tukey HSD: Table of q-statistics
AA AB LAB
==============================
AA 0 2.749 ns 5.330 **
AB 0 2.581 ns
LAB 0
==============================
+ p < .10 (q-critical[3, 381] = 2.91125483514)
* p < .05 (q-critical[3, 381] = 3.32766157576)
** p < .01 (q-critical[3, 381] = 4.14515568451)"""
df = DataFrame()
df.read_tbl('data/suppression~subjectXgroupXageXcycleXphase.csv')
D=df.anova1way('SUPPRESSION', 'GROUP')
self.assertEqual(str(D),R)
def test2(self):
R="""Anova: Single Factor on SUPPRESSION
SUMMARY
Groups Count Sum Average Variance
==============================================
AA 128 2048 16 148.792
AB 128 2510.600 19.614 250.326
LAB 128 2945.000 23.008 264.699
ANOVA
Source of SS df MS F P-value
Variation
===========================================================
Treatments 3144.039 2 1572.020 7.104 9.348e-04
Error 84304.687 381 221.272
===========================================================
Total 87448.726 383 """
df = DataFrame()
df.read_tbl('suppression~subjectXgroupXageXcycleXphase.csv')
aov=df.anova1way('SUPPRESSION','GROUP')
self.assertEqual(str(aov),R)
# instantiate DataFrame object to hold data
df = DataFrame() # inherents a dict
# put data into a DataFrame object
df['data'] = data1 + data2
# build dummy code column
df['conditions'] = ['A'] * len(data1) + ['B'] * len(data2)
# visually verify data in DataFrame
print(df)
# run 1 way analysis of variance
# returns another dict-like object
aov = df.anova1way('data', 'conditions')
# print anova results
print(aov)
# this is just to show the data in the aov object
print(aov.keys())
# calculate omega-squared
aov['omega-sq'] = (aov['ssbn'] - aov['dfbn']*aov['mswn']) / \
(aov['ssbn'] + aov['sswn'] + aov['mswn'])
# you can access the results this way
print(aov['omega-sq'])
print(aov['f'])
print(aov['p'])
'''
elif (types == "wanara" or types == "jatayu"):
group = "other"
'''
else:
group = "other"
csv += "\n%s,%s,%s" % (counter, number, group)
counter += 1;
with open("../data/" + measurement +"_zerocrossings_groups.csv", "w") as file:
file.write(csv.decode('utf-8').encode('utf-8'))
print "File created"
datafile="../data/" + measurement +"_zerocrossings_groups.csv"
data = pd.read_csv(datafile)
#Create a boxplot
data.boxplot('crossings', by='group', figsize=(12, 8))
#plt.show()
plt.savefig("../data/" + measurement + '.png', bbox_inches='tight')
#ANOVA
df=DataFrame()
df.read_tbl(datafile)
aov_pyvttbl = df.anova1way('crossings', 'group')
#print aov_pyvttbl
with open("../data/" + measurement +"_ANOVA.txt", "w") as file:
file.write(str(aov_pyvttbl))
print "ANOVA File created"
# instantiate DataFrame object to hold data
df = DataFrame() # inherents a dict
# put data into a DataFrame object
df['data'] = data1+data2
# build dummy code column
df['conditions'] = ['A']*len(data1)+['B']*len(data2)
# visually verify data in DataFrame
print(df)
# run 1 way analysis of variance
# returns another dict-like object
aov = df.anova1way('data', 'conditions')
# print anova results
print(aov)
# this is just to show the data in the aov object
print(aov.keys())
# calculate omega-squared
aov['omega-sq'] = (aov['ssbn'] - aov['dfbn']*aov['mswn']) / \
(aov['ssbn'] + aov['sswn'] + aov['mswn'])
# you can access the results this way
print(aov['omega-sq'])
print(aov['f'])
print(aov['p'])
#!C:\python27\python
from pyvttbl import DataFrame
datafile = "C:\\Users\\radhapavan\\Desktop\\Alex\\anova.csv"
df = DataFrame()
df.read_tbl(datafile)
aov_pyvttbl = df.anova1way('deal_probability', 'parent_category_name')
print aov_pyvttbl
import pandas as pd
datafile = "PlantGrowth.csv"
data = pd.read_csv(datafile)
#Create a boxplot
data.boxplot('weight', by='group', figsize=(12, 8))
ctrl = data['weight'][data.group == 'ctrl']
grps = pd.unique(data.group.values)
d_data = {grp:data['weight'][data.group == grp] \
for grp in pd.unique(data.group.values)}
k = len(pd.unique(data.group)) # number of conditions
N = len(data.values) # conditions times participants
n = data.groupby('group').size()[0] #Participants in each condition
from pyvttbl import DataFrame
df = DataFrame()
df.read_tbl(datafile)
aov_pyvttbl = df.anova1way('weight', 'group')
print(aov_pyvttbl)
