notebook.community

Edit and run 





In [1]:



    


drive_path = 'c:/'
import numpy as np
import pandas as pd
import os
import sys
import matplotlib.pyplot as plt
from scipy.stats import ks_2samp
from scipy.stats import anderson_ksamp
from scipy.stats import kruskal
from scipy.stats import variation
%matplotlib inline
import seaborn as sns
from scipy.stats import zscore
from scipy.stats import nanmean
from scipy.stats import nanstd
from scipy.cluster.hierarchy import dendrogram, linkage



    











In [2]:



    


filename='C:\Users\Annie\Documents\Data\Ca_Imaging\Analysis\\Odor_Panel\\Odor_Trials.csv'
trials=pd.read_csv(filename)



    











In [3]:



    


z='C:\Users\Annie\Documents\Data\Ca_Imaging\GoodFiles\\fullpeak_WL.csv'
peak=pd.read_csv(z)
s='C:\Users\Annie\Documents\Data\Ca_Imaging\GoodFiles\\fullsuccess_WI.csv'
success=pd.read_csv(s)

Reliability vs Peak





In [4]:



    


melt_success=pd.melt(success,('Mouse','Group'),var_name='Odor',value_name='Reliability')
melt_peak=pd.melt(peak,('Mouse','Group'),var_name='Odor',value_name='Peak')



    











In [5]:



    


peak.head()



    


















    
Out[5]:










  
    

      
      Group
      Mouse
      IAA10
      IAA01
      AP
      MS10
      IAA05
      Hexanal01
      EB
      MS01
      PA
      MS05
      Blank
      Hexanone
      Hexanal10
      THA
      Hexanal05
    

  
  
    

      0
      Control
      G PMT (1)_160321_1
      0.099708
      0.188597
      0.036738
      0.150474
      0.034294
      0.062999
      -0.061840
      0.015671
      0.037389
      0.169456
      NaN
      0.093353
      0.069948
      0.067358
      0.124211
    

    

      1
      Control
      G PMT (2)_160321_1
      0.041676
      0.188666
      0.073576
      0.074001
      0.001814
      0.014205
      0.056893
      -0.034636
      -0.002271
      0.139423
      NaN
      -0.026087
      0.036447
      0.095266
      0.101018
    

    

      2
      Control
      G PMT (3)_160321_1
      0.287615
      0.477065
      0.058214
      0.260675
      0.127803
      0.129928
      0.153817
      -0.044179
      0.221412
      0.095906
      NaN
      0.022945
      0.263380
      0.146676
      0.293199
    

    

      3
      Control
      G PMT (4)_160321_1
      0.034975
      0.248613
      0.110235
      0.071141
      0.104363
      0.104142
      0.082859
      0.146939
      0.051386
      0.157300
      NaN
      -0.057530
      0.037260
      0.094015
      0.198974
    

    

      4
      Control
      G PMT (5)_160321_1
      0.309290
      0.393188
      0.116399
      0.220858
      0.240154
      0.315627
      0.694684
      0.268299
      0.203381
      0.233311
      NaN
      -0.147715
      0.145721
      0.069755
      0.538062
    

  




















In [6]:



    


success_peak=pd.concat([melt_peak,melt_success.Reliability],axis=1)
control=success_peak[success_peak['Group']=='Control']
mint=success_peak[success_peak['Group']=='Mint']
hexanal=success_peak[success_peak['Group']=='Hexanal']



    











In [7]:



    


sns.set(style='white',palette="muted", color_codes=True);
sns.set_context("paper",font_scale=2);
ax=sns.barplot(x='Reliability',y='Peak',hue='Group',data=success_peak, palette=['black',sns.xkcd_rgb['azure'],sns.xkcd_rgb['grey']],hue_order=['Control','Hexanal','Mint']);

ax.set(xlabel='Reliability', ylabel='Peak')
ax.set_xticklabels([0,0.25,0.33,0.5,0.66,0.75,1.0])
sns.despine(left=True,bottom=True);
plt.tight_layout();

plt.savefig("C:\Users\Annie\Desktop\Plasticity\Figures\Excitatory\Success_Peak.pdf")



    


















    
























In [42]:



    


sns.set(style='white',palette="muted", color_codes=True);
sns.set_context("paper",font_scale=2);
sns.barplot(x='Reliability',y='Peak',data=hexanal);
# plt.ylim(0,5)
plt.tight_layout();



    


















    
























In [41]:



    


sns.set(style='white',palette="muted", color_codes=True);
sns.set_context("paper",font_scale=2);
sns.barplot(x='Reliability',y='Peak',data=mint);
plt.xl
# plt.ylim(0,5)
plt.tight_layout();



    


















    
























In [33]:



    


sns.set(style='white',palette="muted", color_codes=True);
sns.set_context("paper",font_scale=2);
sns.jointplot('Reliability','Peak',mint).set_axis_labels("Reliability", "Peak");
# sns.jointplot('Reliability','Peak',hexanal).set_axis_labels('Reliability','Peak');
sns.despine(left=True,bottom=True);
plt.ylim(0,5)
plt.tight_layout();



    


















    
























In [29]:



    


sns.set(style='white',palette="muted", color_codes=True);
sns.set_context("paper",font_scale=2);
sns.jointplot('Reliability','Peak',hexanal).set_axis_labels('Reliability','Peak');
sns.despine(left=True,bottom=True);
plt.ylim(0,5)
plt.tight_layout();



    


















    
























In [30]:



    


sns.set(style='white',palette="muted", color_codes=True);
sns.set_context("paper",font_scale=2);
sns.jointplot('Reliability','Peak',control).set_axis_labels('Reliability','Peak');
sns.despine(left=True,bottom=True);
plt.ylim(0,5)
plt.tight_layout();



    


















    
























In [40]:



    


sns.set(style='white',palette="muted", color_codes=True);
sns.set_context("paper",font_scale=2);
sns.jointplot('Peak','Reliability',success_peak).set_axis_labels("Peak DF/F", "Baseline Fluorescence");
sns.despine(left=True,bottom=True);
plt.tight_layout();

KMeans





In [8]:



    


import numpy as np
from kmodes import kmodes



    


















    






---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-8-9ad5e0d12599> in <module>()
      1 import numpy as np
----> 2 from kmodes import kmodes

ImportError: No module named kmodes
















In [9]:



    


import kmodes



    


















    






---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-9-13e229bcbe6d> in <module>()
----> 1 import kmodes

ImportError: No module named kmodes
















In [ ]:



    


# random categorical data
data = np.random.choice(20, (100, 10))

km = kmodes.KModes(n_clusters=4, init='Huang', n_init=5, verbose=1)

clusters = km.fit_predict(data)

# Print the cluster centroids
print(km.cluster_centroids_)



    











In [85]:



    


c=peak[peak.Group=='Control'].ix[:,2:]



    











In [86]:



    


k=2
kmeans = cluster.KMeans(n_clusters=k)
kmeans.fit(c)



    


















    






---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-86-611175834ee9> in <module>()
      1 k=2
      2 kmeans = cluster.KMeans(n_clusters=k)
----> 3 kmeans.fit(c)

C:\Users\Annie\Anaconda2\lib\site-packages\sklearn\cluster\k_means_.py in fit(self, X, y)
    810         """
    811         random_state = check_random_state(self.random_state)
--> 812         X = self._check_fit_data(X)
    813 
    814         self.cluster_centers_, self.labels_, self.inertia_, self.n_iter_ = \

C:\Users\Annie\Anaconda2\lib\site-packages\sklearn\cluster\k_means_.py in _check_fit_data(self, X)
    784     def _check_fit_data(self, X):
    785         """Verify that the number of samples given is larger than k"""
--> 786         X = check_array(X, accept_sparse='csr', dtype=np.float64)
    787         if X.shape[0] < self.n_clusters:
    788             raise ValueError("n_samples=%d should be >= n_clusters=%d" % (

C:\Users\Annie\Anaconda2\lib\site-packages\sklearn\utils\validation.pyc in check_array(array, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    396                              % (array.ndim, estimator_name))
    397         if force_all_finite:
--> 398             _assert_all_finite(array)
    399 
    400     shape_repr = _shape_repr(array.shape)

C:\Users\Annie\Anaconda2\lib\site-packages\sklearn\utils\validation.pyc in _assert_all_finite(X)
     52             and not np.isfinite(X).all()):
     53         raise ValueError("Input contains NaN, infinity"
---> 54                          " or a value too large for %r." % X.dtype)
     55 
     56 

ValueError: Input contains NaN, infinity or a value too large for dtype('float64').

Separating by sex





In [4]:



    


control=peak[peak['Group']=='Control']
mint=peak[peak['Group']=='Mint']
hexanal=peak[peak['Group']=='Hexanal']



    











In [5]:



    


# control.to_csv('C:\Users\Annie\Desktop\\Plasticity\\controlpeaks.csv')
# mint.to_csv('C:\Users\Annie\Desktop\\Plasticity\\mintpeaks.csv')
# hexanal.to_csv('C:\Users\Annie\Desktop\\Plasticity\\hexanalpeaks.csv')



    











In [6]:



    


c=pd.read_csv('C:\Users\Annie\Desktop\\Plasticity\\controlpeaks.csv')
m=pd.read_csv('C:\Users\Annie\Desktop\\Plasticity\\mintpeaks.csv')
h=pd.read_csv('C:\Users\Annie\Desktop\\Plasticity\\hexanalpeaks.csv')



    











In [7]:



    


cmelt=pd.melt(c,('Group','Mouse','Sex'),var_name='Odor',value_name='Peak')
mmelt=pd.melt(m,('Group','Mouse','Sex'),var_name='Odor',value_name='Peak')
hmelt=pd.melt(h,('Group','Mouse','Sex'),var_name='Odor',value_name='Peak')



    











In [8]:



    


cexcite=cmelt[cmelt.Peak>0]
mexcite=mmelt[mmelt.Peak>0]
hexcite=hmelt[hmelt.Peak>0]



    











In [9]:



    


allexcite=pd.concat([cexcite, mexcite, hexcite])
allexcitem=allexcite[allexcite.Sex=='M']
allexcitef=allexcite[allexcite.Sex=='F']



    











In [10]:



    


cmale=cexcite[cexcite.Sex=='M']
cfemale=cexcite[cexcite.Sex=='F']
mmale=mexcite[mexcite.Sex=='M']
mfemale=mexcite[mexcite.Sex=='F']
hmale=hexcite[hexcite.Sex=='M']
hfemale=hexcite[hexcite.Sex=='F']



    











In [9]:



    


cmale



    


















    






C:\Users\Annie\Anaconda2\lib\site-packages\scipy\stats\stats.py:257: RuntimeWarning: The input array could not be properly checked for nan values. nan values will be ignored.
  "values. nan values will be ignored.", RuntimeWarning)










    
Out[9]:








KruskalResult(statistic=32751.358102116363, pvalue=0.0)

Graphs





In [23]:



    


ecm=cmale[cmale.Peak>0]
ecf=cfemale[cfemale.Peak>0]
ecm.Peak.plot.hist(alpha=0.5);
ecf.Peak.plot.hist(alpha=0.5);
sns.set(style='white',palette="muted", color_codes=True);
sns.set_style("ticks")
plt.xlim(0,5);
plt.title('Control')
sns.despine()
plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\Control.pdf")



    


















    
























In [9]:



    


emm=mmale[mmale.Peak>0]
emf=mfemale[mfemale.Peak>0]
emm.Peak.plot.hist(alpha=0.5);
emf.Peak.plot.hist(alpha=0.5);
sns.set(style='white',palette="muted", color_codes=True);
sns.set_style("ticks")
plt.title('Mint')
plt.xlim(0,5);
sns.despine()
# plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\Mint.pdf")



    


















    
























In [10]:



    


ehm=hmale[hmale.Peak>0]
ehf=hfemale[hfemale.Peak>0]
ehm.Peak.plot.hist(alpha=0.5);
ehf.Peak.plot.hist(alpha=0.5);
sns.set(style='white',palette="muted", color_codes=True);
sns.set_style("ticks")
plt.xlim(0,5);
plt.title('Hexanal')
sns.despine()
# plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\Hexanal.pdf")



    


















    
























In [16]:



    


sns.set(style='white');
sns.set_style("ticks")
sns.set_context("paper",font_scale=2);
x=allexcitem[allexcitem.Group=='Control'].Peak.dropna();
y=allexcitem[allexcitem.Group=='Hexanal'].Peak.dropna();
z=allexcitem[allexcitem.Group=='Mint'].Peak.dropna();
sns.kdeplot(x,cumulative=True,color='black',lw=3,label='Control')
sns.kdeplot(y,cumulative=True,color=sns.xkcd_rgb["azure"],lw=3,label='Hexanal')
sns.kdeplot(z,cumulative=True,color=sns.xkcd_rgb['grey'],lw=3,label='Mint')
sns.despine();
plt.tight_layout();
plt.xlabel('Peak');
plt.ylabel('Density Function');
plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\maledis.pdf")



    


















    
























In [17]:



    


sns.set(style='white');
sns.set_style("ticks")
sns.set_context("paper",font_scale=2);
x=allexcitef[allexcitef.Group=='Control'].Peak.dropna();
y=allexcitef[allexcitef.Group=='Hexanal'].Peak.dropna();
z=allexcitef[allexcitef.Group=='Mint'].Peak.dropna();
sns.kdeplot(x,cumulative=True,color='black',lw=3,label='Control')
sns.kdeplot(y,cumulative=True,color=sns.xkcd_rgb["azure"],lw=3,label='Hexanal')
sns.kdeplot(z,cumulative=True,color=sns.xkcd_rgb['grey'],lw=3,label='Mint')
sns.despine();
plt.tight_layout();
plt.xlabel('Peak');
plt.ylabel('Density Function');
plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\\femaledis.pdf")



    


















    
























In [87]:



    


mfemale.Peak.plot.hist(alpha=0.5)
# mmale.Peak.plot.hist(alpha=1)
cfemale.Peak.plot.hist(alpha=0.5)
# cmale.Peak.plot.hist(alpha=0.5)
# hfemale.Peak.plot.hist(alpha=0.5)
# hmale.Peak.plot.hist(alpha=0.5)



    


















    
Out[87]:








<matplotlib.axes._subplots.AxesSubplot at 0x10ec9240>










    
























In [26]:



    


kruskal(mmale.Peak,hmale.Peak.dropna())



    


















    
Out[26]:








KruskalResult(statistic=267.46565663999354, pvalue=4.0482546677391195e-60)

















In [19]:



    


cat=('M','F')
sns.set(style="white", palette="muted", color_codes=True);
sns.set_context("paper", font_scale=1.3);
plt.figure(figsize=(8.5,5));
sns.boxplot(x='Odor',y='Peak',hue_order=cat,hue='Sex',data=mexcite);
# ax.legend_.remove()
sns.despine()
plt.ylabel('DF/F', fontsize=12);
plt.title('Peak DF/F, 1%, Mint', fontsize=12);
plt.xlabel('Odor', fontsize=12);
plt.ylim(-1,5)
plt.tight_layout()
plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\Mint_e.pdf")



    


















    
























In [20]:



    


at=('M','F')
sns.set(style="white", palette="muted", color_codes=True);
sns.set_context("paper", font_scale=1.3);
plt.figure(figsize=(9,5));
sns.boxplot(x='Odor',y='Peak',hue_order=cat,hue='Sex',data=hexcite);
# ax.legend_.remove()
sns.despine()
plt.ylabel('DF/F', fontsize=12);
plt.title('Peak DF/F, 1%, Hexanal', fontsize=12);
plt.xlabel('Odor', fontsize=12);
plt.ylim(-1,5)
plt.tight_layout()
plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\hexanal_e.pdf")



    


















    
























In [22]:



    


at=('M','F')
sns.set(style="white", palette="muted", color_codes=True);
sns.set_context("paper", font_scale=1.3);
plt.figure(figsize=(9,5));
sns.boxplot(x='Odor',y='Peak',hue_order=cat,hue='Sex',data=cexcite);
# ax.legend_.remove()
sns.despine()
plt.ylabel('DF/F', fontsize=12);
plt.title('Peak DF/F, 1%, Control', fontsize=12);
plt.xlabel('Odor', fontsize=12);
plt.ylim(-1,5)
plt.tight_layout()
plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\Control_e.pdf")



    


















    
























In [37]:



    


allexcitef.tail()



    


















    
Out[37]:










  
    

      
      Group
      Mouse
      Sex
      Odor
      Peak
    

  
  
    

      5161
      Hexanal
      G PMT (22)_160626_2
      F
      Hexanal05
      2.629784
    

    

      5162
      Hexanal
      G PMT (23)_160626_2
      F
      Hexanal05
      2.228448
    

    

      5163
      Hexanal
      G PMT (24)_160626_2
      F
      Hexanal05
      2.581529
    

    

      5164
      Hexanal
      G PMT (25)_160626_2
      F
      Hexanal05
      1.906673
    

    

      5165
      Hexanal
      G PMT (26)_160626_2
      F
      Hexanal05
      2.273161
    

  




















In [43]:



    


# at=('M','F')
sns.set(style="white", palette="muted", color_codes=True);
sns.set_context("paper", font_scale=1.3);
plt.figure(figsize=(9,5));
sns.boxplot(x='Odor',y='Peak',hue='Group',data=allexcitef);
# ax.legend_.remove()
sns.despine()
plt.ylabel('DF/F', fontsize=12);
plt.title('Peak DF/F, 1%, Female', fontsize=12);
plt.xlabel('Odor', fontsize=12);
plt.ylim(-1,5)
plt.tight_layout()
plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\\allfemale.pdf")



    


















    
























In [45]:



    


# at=('M','F')
sns.set(style="white", palette="muted", color_codes=True);
sns.set_context("paper", font_scale=1.3);
plt.figure(figsize=(9,5));
sns.boxplot(x='Odor',y='Peak',hue='Group',data=allexcitem);
# ax.legend_.remove()
sns.despine()
plt.ylabel('DF/F', fontsize=12);
plt.title('Peak DF/F, 1%, Male', fontsize=12);
plt.xlabel('Odor', fontsize=12);
plt.ylim(-1,5)
plt.tight_layout()
plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\\allmale.pdf")



    


















    
























In [47]:



    


# at=('M','F')
sns.set(style="white", palette="muted", color_codes=True);
sns.set_context("paper", font_scale=1.3);
plt.figure(figsize=(9,5));
sns.boxplot(x='Odor',y='Peak',hue='Group',data=allexcite);
# ax.legend_.remove()
sns.despine()
plt.ylabel('DF/F', fontsize=12);
plt.title('Peak DF/F, 1%, All', fontsize=12);
plt.xlabel('Odor', fontsize=12);
plt.ylim(-1,5)
plt.tight_layout()
plt.savefig("C:\Users\Annie\Desktop\Plasticity\Revision\SexDiff\\all.pdf")

Dendrogram





In [27]:



    


peak.head()



    


















    
Out[27]:










  
    

      
      Group
      Mouse
      IAA10
      IAA01
      AP
      MS10
      IAA05
      Hexanal01
      EB
      MS01
      PA
      MS05
      Blank
      Hexanone
      Hexanal10
      THA
      Hexanal05
    

  
  
    

      0
      Control
      G PMT (1)_160321_1
      0.099708
      0.188597
      0.036738
      0.150474
      0.034294
      0.062999
      -0.061840
      0.015671
      0.037389
      0.169456
      NaN
      0.093353
      0.069948
      0.067358
      0.124211
    

    

      1
      Control
      G PMT (2)_160321_1
      0.041676
      0.188666
      0.073576
      0.074001
      0.001814
      0.014205
      0.056893
      -0.034636
      -0.002271
      0.139423
      NaN
      -0.026087
      0.036447
      0.095266
      0.101018
    

    

      2
      Control
      G PMT (3)_160321_1
      0.287615
      0.477065
      0.058214
      0.260675
      0.127803
      0.129928
      0.153817
      -0.044179
      0.221412
      0.095906
      NaN
      0.022945
      0.263380
      0.146676
      0.293199
    

    

      3
      Control
      G PMT (4)_160321_1
      0.034975
      0.248613
      0.110235
      0.071141
      0.104363
      0.104142
      0.082859
      0.146939
      0.051386
      0.157300
      NaN
      -0.057530
      0.037260
      0.094015
      0.198974
    

    

      4
      Control
      G PMT (5)_160321_1
      0.309290
      0.393188
      0.116399
      0.220858
      0.240154
      0.315627
      0.694684
      0.268299
      0.203381
      0.233311
      NaN
      -0.147715
      0.145721
      0.069755
      0.538062
    

  




















In [33]:



    


cpeak=peak[peak.Group=='Control']
mpeak=peak[peak.Group=='Mint']
hpeak=peak[peak.Group=='Hexanal']



    











In [34]:



    


X=peak[['IAA10','IAA01','AP','MS10','IAA05','Hexanal01','EB','MS01','PA','MS05','Hexanone','Hexanal10','THA','Hexanal05']]
C=cpeak[['IAA10','IAA01','AP','MS10','IAA05','Hexanal01','EB','MS01','PA','MS05','Hexanone','Hexanal10','THA','Hexanal05']]
M=mpeak[['IAA10','IAA01','AP','MS10','IAA05','Hexanal01','EB','MS01','PA','MS05','Hexanone','Hexanal10','THA','Hexanal05']]
H=hpeak[['IAA10','IAA01','AP','MS10','IAA05','Hexanal01','EB','MS01','PA','MS05','Hexanone','Hexanal10','THA','Hexanal05']]



    











In [35]:



    


Z=linkage(X)
CZ=linkage(C)
MZ=linkage(M)
HZ=linkage(H)



    











In [20]:



    


from scipy.cluster.hierarchy import cophenet
from scipy.spatial.distance import pdist



    











In [39]:



    


pd.DataFrame(HZ)



    


















    
Out[39]:










  
    

      
      0
      1
      2
      3
    

  
  
    

      0
      238.0
      239.0
      0.100247
      2.0
    

    

      1
      240.0
      246.0
      0.110695
      2.0
    

    

      2
      338.0
      339.0
      0.113964
      2.0
    

    

      3
      122.0
      126.0
      0.115886
      2.0
    

    

      4
      216.0
      225.0
      0.115988
      2.0
    

    

      5
      46.0
      229.0
      0.124773
      2.0
    

    

      6
      331.0
      333.0
      0.128011
      2.0
    

    

      7
      329.0
      375.0
      0.134020
      3.0
    

    

      8
      130.0
      137.0
      0.136090
      2.0
    

    

      9
      121.0
      134.0
      0.136509
      2.0
    

    

      10
      242.0
      243.0
      0.137313
      2.0
    

    

      11
      13.0
      14.0
      0.140912
      2.0
    

    

      12
      210.0
      211.0
      0.145379
      2.0
    

    

      13
      23.0
      380.0
      0.147315
      3.0
    

    

      14
      372.0
      377.0
      0.148624
      4.0
    

    

      15
      332.0
      340.0
      0.149896
      2.0
    

    

      16
      72.0
      78.0
      0.150523
      2.0
    

    

      17
      199.0
      209.0
      0.152150
      2.0
    

    

      18
      233.0
      369.0
      0.152667
      3.0
    

    

      19
      80.0
      84.0
      0.153193
      2.0
    

    

      20
      230.0
      374.0
      0.153480
      3.0
    

    

      21
      370.0
      387.0
      0.153750
      5.0
    

    

      22
      271.0
      272.0
      0.153828
      2.0
    

    

      23
      236.0
      379.0
      0.156002
      3.0
    

    

      24
      120.0
      378.0
      0.158685
      3.0
    

    

      25
      129.0
      383.0
      0.158714
      5.0
    

    

      26
      237.0
      390.0
      0.159039
      6.0
    

    

      27
      342.0
      384.0
      0.159053
      3.0
    

    

      28
      67.0
      82.0
      0.159960
      2.0
    

    

      29
      220.0
      224.0
      0.161044
      2.0
    

    

      ...
      ...
      ...
      ...
      ...
    

    

      338
      695.0
      703.0
      0.725884
      6.0
    

    

      339
      155.0
      706.0
      0.733385
      333.0
    

    

      340
      287.0
      708.0
      0.743016
      334.0
    

    

      341
      365.0
      707.0
      0.753560
      7.0
    

    

      342
      699.0
      709.0
      0.754472
      336.0
    

    

      343
      696.0
      710.0
      0.754626
      9.0
    

    

      344
      141.0
      711.0
      0.756929
      337.0
    

    

      345
      205.0
      713.0
      0.773977
      338.0
    

    

      346
      366.0
      712.0
      0.782250
      10.0
    

    

      347
      170.0
      714.0
      0.791842
      339.0
    

    

      348
      351.0
      715.0
      0.800248
      11.0
    

    

      349
      343.0
      363.0
      0.807511
      2.0
    

    

      350
      358.0
      716.0
      0.816226
      340.0
    

    

      351
      718.0
      719.0
      0.825686
      342.0
    

    

      352
      190.0
      720.0
      0.858784
      343.0
    

    

      353
      21.0
      721.0
      0.861141
      344.0
    

    

      354
      267.0
      717.0
      0.873012
      12.0
    

    

      355
      327.0
      722.0
      0.879714
      345.0
    

    

      356
      326.0
      724.0
      0.886699
      346.0
    

    

      357
      723.0
      725.0
      0.908697
      358.0
    

    

      358
      266.0
      726.0
      0.909234
      359.0
    

    

      359
      169.0
      189.0
      0.928817
      2.0
    

    

      360
      295.0
      727.0
      0.943164
      360.0
    

    

      361
      191.0
      729.0
      0.949116
      361.0
    

    

      362
      581.0
      730.0
      1.067565
      363.0
    

    

      363
      252.0
      731.0
      1.152794
      364.0
    

    

      364
      182.0
      728.0
      1.161500
      3.0
    

    

      365
      183.0
      733.0
      1.237995
      4.0
    

    

      366
      732.0
      734.0
      1.438012
      368.0
    

    

      367
      181.0
      735.0
      2.243542
      369.0
    

  



368 rows × 4 columns



















In [10]:



    


c, coph_dists=cophenet(Z,pdist(X))
c



    


















    
Out[10]:








nan

















In [30]:



    


pd.DataFrame(Z)



    


















    
Out[30]:










  
    

      
      0
      1
      2
      3
    

  
  
    

      0
      732.0
      733.0
      0.100247
      2.0
    

    

      1
      345.0
      350.0
      0.102388
      2.0
    

    

      2
      734.0
      740.0
      0.110695
      2.0
    

    

      3
      832.0
      833.0
      0.113964
      2.0
    

    

      4
      426.0
      719.0
      0.114798
      2.0
    

    

      5
      616.0
      620.0
      0.115886
      2.0
    

    

      6
      710.0
      867.0
      0.115988
      3.0
    

    

      7
      366.0
      379.0
      0.116976
      2.0
    

    

      8
      123.0
      132.0
      0.118534
      2.0
    

    

      9
      249.0
      259.0
      0.118667
      2.0
    

    

      10
      51.0
      872.0
      0.121240
      3.0
    

    

      11
      420.0
      868.0
      0.121326
      3.0
    

    

      12
      390.0
      396.0
      0.123074
      2.0
    

    

      13
      540.0
      723.0
      0.124773
      2.0
    

    

      14
      199.0
      430.0
      0.127480
      2.0
    

    

      15
      825.0
      827.0
      0.128011
      2.0
    

    

      16
      216.0
      224.0
      0.133782
      2.0
    

    

      17
      367.0
      870.0
      0.133796
      3.0
    

    

      18
      823.0
      878.0
      0.134020
      3.0
    

    

      19
      362.0
      365.0
      0.134205
      2.0
    

    

      20
      624.0
      631.0
      0.136090
      2.0
    

    

      21
      615.0
      628.0
      0.136509
      2.0
    

    

      22
      736.0
      737.0
      0.137313
      2.0
    

    

      23
      363.0
      380.0
      0.137672
      2.0
    

    

      24
      210.0
      211.0
      0.139673
      2.0
    

    

      25
      190.0
      207.0
      0.140415
      2.0
    

    

      26
      507.0
      508.0
      0.140912
      2.0
    

    

      27
      368.0
      886.0
      0.140936
      3.0
    

    

      28
      425.0
      435.0
      0.141590
      2.0
    

    

      29
      372.0
      880.0
      0.141912
      4.0
    

    

      ...
      ...
      ...
      ...
      ...
    

    

      832
      635.0
      1694.0
      0.756929
      825.0
    

    

      833
      488.0
      1695.0
      0.763333
      826.0
    

    

      834
      699.0
      1696.0
      0.773977
      827.0
    

    

      835
      860.0
      1693.0
      0.782250
      10.0
    

    

      836
      515.0
      1697.0
      0.783003
      828.0
    

    

      837
      664.0
      1699.0
      0.791842
      829.0
    

    

      838
      845.0
      1698.0
      0.800248
      11.0
    

    

      839
      837.0
      857.0
      0.807511
      2.0
    

    

      840
      852.0
      1700.0
      0.816226
      830.0
    

    

      841
      1702.0
      1703.0
      0.825686
      832.0
    

    

      842
      820.0
      1704.0
      0.834828
      833.0
    

    

      843
      684.0
      1705.0
      0.858784
      834.0
    

    

      844
      761.0
      1701.0
      0.873012
      12.0
    

    

      845
      821.0
      1706.0
      0.879714
      835.0
    

    

      846
      1707.0
      1708.0
      0.908697
      847.0
    

    

      847
      760.0
      1709.0
      0.909234
      848.0
    

    

      848
      663.0
      683.0
      0.928817
      2.0
    

    

      849
      171.0
      1710.0
      0.930779
      849.0
    

    

      850
      789.0
      1712.0
      0.943164
      850.0
    

    

      851
      685.0
      1713.0
      0.949116
      851.0
    

    

      852
      141.0
      1714.0
      0.958611
      852.0
    

    

      853
      88.0
      1715.0
      0.994161
      853.0
    

    

      854
      89.0
      1716.0
      1.001268
      854.0
    

    

      855
      1470.0
      1717.0
      1.067565
      856.0
    

    

      856
      746.0
      1718.0
      1.152794
      857.0
    

    

      857
      676.0
      1711.0
      1.161500
      3.0
    

    

      858
      677.0
      1720.0
      1.237995
      4.0
    

    

      859
      1719.0
      1721.0
      1.438012
      861.0
    

    

      860
      675.0
      1722.0
      2.243542
      862.0
    

    

      861
      70.0
      1723.0
      inf
      863.0
    

  



862 rows × 4 columns



















In [23]:



    


plt.figure(figsize=(25,10))
plt.title('Hierarchical Clustering Dendrogram')
plt.xlabel('sample index')
plt.ylabel('distance')
dendrogram(Z,leaf_rotation=90., leaf_font_size=8.)
plt.show()



    


















    






---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-23-13e399ac5af4> in <module>()
      3 plt.xlabel('sample index')
      4 plt.ylabel('distance')
----> 5 dendrogram(Z,leaf_rotation=90., leaf_font_size=8.)
      6 plt.show()

C:\Users\Annie\Anaconda2\lib\site-packages\scipy\cluster\hierarchy.pyc in dendrogram(Z, p, truncate_mode, color_threshold, get_leaves, orientation, labels, count_sort, distance_sort, show_leaf_counts, no_plot, no_labels, leaf_font_size, leaf_rotation, leaf_label_func, show_contracted, link_color_func, ax, above_threshold_color)
   2228                          "'bottom', or 'right'")
   2229 
-> 2230     is_valid_linkage(Z, throw=True, name='Z')
   2231     Zs = Z.shape
   2232     n = Zs[0] + 1

C:\Users\Annie\Anaconda2\lib\site-packages\scipy\cluster\hierarchy.pyc in is_valid_linkage(Z, warning, throw, name)
   1410             if ((Z[:, 0] < 0).any() or (Z[:, 1] < 0).any()):
   1411                 raise ValueError('Linkage %scontains negative indices.' %
-> 1412                                  name_str)
   1413             if (Z[:, 2] < 0).any():
   1414                 raise ValueError('Linkage %scontains negative distances.' %

ValueError: Linkage 'Z' contains negative indices.









    
























In [ ]:

Content source: liu-annie/CaI

Similar notebooks:

notebook.community | gallery | about