Revision c457778e timeAnalysis.py
| timeAnalysis.py | ||
|---|---|---|
| 18 | 18 |
|
| 19 | 19 |
|
| 20 | 20 |
folder = sys.argv[1] |
| 21 |
lags = int(sys.argv[2]) |
|
| 21 |
lags = 100 |
|
| 22 |
if len(sys.argv) > 2: |
|
| 23 |
lags = int(sys.argv[2]) |
|
| 22 | 24 |
nick = folder.split('/')[-2].split('_')[0]+"_"
|
| 23 | 25 |
os.chdir(folder) |
| 24 | 26 |
|
| 25 |
dfn = pd.DataFrame() # rows=nodes columns=BC at column-index time-instant |
|
| 27 |
bcdf = pd.DataFrame() # rows=nodes columns=BC at column-index time-instant |
|
| 28 |
degdf = pd.DataFrame() # rows=nodes columns=DEG at column-index time-instant |
|
| 29 |
kcoredf = pd.DataFrame() # rows=nodes columns=KCORE at column-index time-instant |
|
| 26 | 30 |
print "Loading data from", folder, "..." |
| 27 | 31 |
for snap in sorted(glob.glob('./stats*')):
|
| 28 |
# print snap |
|
| 32 |
# print "",snap
|
|
| 29 | 33 |
node_id = int(snap.strip('.csv').strip('./stats'))
|
| 30 |
df = pd.read_csv(snap, names=['time', str(node_id)], skiprows=1) |
|
| 31 |
dfn = pd.concat([dfn, df[str(node_id)]], axis=1) |
|
| 34 |
df = pd.read_csv(snap, names=['time', 'bc', 'deg', 'kcore'], skiprows=1) |
|
| 35 |
bcdf = pd.concat([bcdf, df['bc']], axis=1) |
|
| 36 |
degdf = pd.concat([degdf, df['deg']], axis=1) |
|
| 37 |
kcoredf = pd.concat([kcoredf, df['kcore']], axis=1) |
|
| 32 | 38 |
|
| 33 | 39 |
|
| 34 |
nodes = dfn.columns.tolist()
|
|
| 40 |
nodes = range(len(bcdf.columns))
|
|
| 35 | 41 |
|
| 36 | 42 |
initialCentrality = {}
|
| 37 | 43 |
for n in nodes: |
| 38 |
initialCentrality[int(n)] = dfn.iloc[0][n]
|
|
| 44 |
initialCentrality[int(n)] = bcdf.iloc[0][n]
|
|
| 39 | 45 |
|
| 40 | 46 |
|
| 41 | 47 |
sorted_x = sorted(initialCentrality.items(), |
| 42 | 48 |
key=operator.itemgetter(1), reverse=True) |
| 43 | 49 |
srtNodes = [e[0] for e in sorted_x] |
| 44 | 50 |
|
| 45 |
dfACF = pd.DataFrame() # rows=Time-Lags, columns = nodes |
|
| 51 |
bcACF = pd.DataFrame() # rows=Time-Lags, columns = nodes |
|
| 52 |
degACF = pd.DataFrame() # rows=Time-Lags, columns = nodes |
|
| 53 |
kcoreACF = pd.DataFrame() # rows=Time-Lags, columns = nodes |
|
| 46 | 54 |
print "Processing data..." |
| 47 | 55 |
for node in nodes: |
| 48 |
#print "Autocorr of node", node |
|
| 49 |
nodeACF = pd.DataFrame([dfn[node].autocorr(lag) for lag in range(lags)]) |
|
| 50 |
dfACF = pd.concat([dfACF, nodeACF], axis=1) |
|
| 51 |
|
|
| 56 |
# print "Autocorr of node", node |
|
| 57 |
nodebcACF = pd.DataFrame([bcdf.iloc[:, node].autocorr(lag) |
|
| 58 |
for lag in range(lags)]) |
|
| 59 |
bcACF = pd.concat([bcACF, nodebcACF], axis=1) |
|
| 60 |
nodedegACF = pd.DataFrame( |
|
| 61 |
[degdf.iloc[:, node].autocorr(lag) for lag in range(lags)]) |
|
| 62 |
degACF = pd.concat([degACF, nodedegACF], axis=1) |
|
| 63 |
nodekcoreACF = pd.DataFrame( |
|
| 64 |
[kcoredf.iloc[:, node].autocorr(lag) for lag in range(lags)]) |
|
| 65 |
kcoreACF = pd.concat([kcoreACF, nodekcoreACF], axis=1) |
|
| 66 |
#code.interact(local=dict(globals(), **locals())) |
|
| 52 | 67 |
|
| 53 | 68 |
''' |
| 54 | 69 |
X ==> time-lag |
| ... | ... | |
| 63 | 78 |
# Plotting |
| 64 | 79 |
# Mean AutoCorrelation and Rank-Correlation |
| 65 | 80 |
# lags=20 |
| 66 |
firstRank = dfn.iloc[0,:]
|
|
| 81 |
firstRank = bcdf.iloc[0, :]
|
|
| 67 | 82 |
x = range(0, lags) |
| 68 |
meanACF = [] |
|
| 83 |
meanbcACF = [] |
|
| 84 |
meandegACF = [] |
|
| 85 |
meankcoreACF = [] |
|
| 69 | 86 |
rankCorr = [] |
| 70 | 87 |
weightedRankCorr = [] |
| 71 | 88 |
for i in x: |
| 72 | 89 |
#code.interact(local=dict(globals(), **locals())) |
| 73 |
meanACF.append(np.mean(dfACF.iloc[i])) |
|
| 74 |
rankCorr.append(stats.spearmanr(firstRank, dfn.iloc[i,:])[0]) |
|
| 90 |
meanbcACF.append(np.mean(bcACF.iloc[i])) |
|
| 91 |
meandegACF.append(np.mean(degACF.iloc[i])) |
|
| 92 |
meankcoreACF.append(np.mean(kcoreACF.iloc[i])) |
|
| 93 |
rankCorr.append(stats.spearmanr(firstRank, bcdf.iloc[i, :])[0]) |
|
| 75 | 94 |
#weightedRankCorr.append(stats.weightedtau(firstRank, dfn.iloc[i,:])[0]) |
| 76 | 95 |
|
| 77 |
plt.plot(x, meanACF, lw="1.5", label='Mean Autocorrelation') |
|
| 96 |
plt.plot(x, meanbcACF, lw="1.5", label='Mean BC Autocorrelation') |
|
| 97 |
plt.plot(x, meandegACF, lw="1.5", label='Mean DEG Autocorrelation') |
|
| 98 |
plt.plot(x, meankcoreACF, lw="1.5", label='Mean KCORE Autocorrelation') |
|
| 78 | 99 |
plt.plot(x, rankCorr, lw="1.5", label='Rank-Correlation (with rank at t_0)') |
| 79 |
#plt.plot(x, weightedRankCorr, lw="1.5", |
|
| 100 |
# plt.plot(x, weightedRankCorr, lw="1.5",
|
|
| 80 | 101 |
# label='Weighted-Rank-Correlation (with rank at t_0)') |
| 81 | 102 |
plt.ylabel('Corr coeff: [ACF, Spearman rho]')
|
| 82 | 103 |
plt.xlabel('Time-lags / Time')
|
| ... | ... | |
| 87 | 108 |
plt.savefig(nick+"autoCorrMean-RankSpearman.pdf", format='pdf') |
| 88 | 109 |
plt.clf() |
| 89 | 110 |
|
| 111 |
toWrite = pd.concat([pd.Series(meanbcACF), pd.Series( |
|
| 112 |
meandegACF), pd.Series(meankcoreACF)], axis=1).iloc[1:, :] |
|
| 113 |
fout = open("meanAC.csv", 'w')
|
|
| 114 |
toWrite.to_csv(fout, index=False) |
|
| 90 | 115 |
|
| 91 | 116 |
''' |
| 92 | 117 |
|
| ... | ... | |
| 127 | 152 |
|
| 128 | 153 |
''' |
| 129 | 154 |
|
| 130 |
X, Y, Z = [], [], [] |
|
| 155 |
'''X, Y, Z = [], [], []
|
|
| 131 | 156 |
for node in srtNodes: |
| 132 | 157 |
#print "n:", node |
| 133 | 158 |
for lag in range(lags): |
| ... | ... | |
| 135 | 160 |
#code.interact(local=dict(globals(), **locals())) |
| 136 | 161 |
X.append(lag) |
| 137 | 162 |
Y.append(node) |
| 138 |
Z.append(list(dfACF.iloc[lag])[node])
|
|
| 163 |
Z.append(list(bcACF.iloc[lag])[node])
|
|
| 139 | 164 |
|
| 140 | 165 |
|
| 141 | 166 |
fig = plt.figure() |
| ... | ... | |
| 147 | 172 |
ax.set_xlim(0, lags) |
| 148 | 173 |
ax.set_ylim(0, len(srtNodes)) |
| 149 | 174 |
#ax.set_zlim(-1.0, 1.0) |
| 150 |
plt.savefig(nick+"autoBC-3d.pdf", format="pdf") |
|
| 175 |
plt.savefig(nick+"autoBC-3d.pdf", format="pdf")'''
|
|
| 151 | 176 |
|
| 152 | 177 |
print "THE END" |
Also available in: Unified diff