diff --git a/Cluster_Analysis.ipynb b/Cluster_Analysis.ipynb
index f1dd1446cb9b22367aef0b44e1c6eaab4db27d79..b1a955bd6f19807ba10f2ba3c20bc06ba00ce703 100644
--- a/Cluster_Analysis.ipynb
+++ b/Cluster_Analysis.ipynb
@@ -27,7 +27,7 @@
"\n",
"# sets min and max parameters for ReqMemCPU\n",
"LowerlimitGB = 0\n",
- "UpperlimitGB = 50"
+ "UpperlimitGB = 50 # gigs per cpu"
]
},
{
@@ -40,7 +40,7 @@
"\n",
"# sets min and max parameters for AllocCPUS\n",
"LowerlimitAllocCPU = 0\n",
- "UpperlimitAllocCPU = 50"
+ "UpperlimitAllocCPU = 50 #cpus"
]
},
{
@@ -53,7 +53,7 @@
"\n",
"# sets min and max parameters for Elapsed\n",
"LowerlimitElapsed = 0\n",
- "UpperlimitElapsed = 150.02"
+ "UpperlimitElapsed = 150.02 #in hours - 6.25 days"
]
},
{
@@ -62,7 +62,7 @@
"metadata": {},
"outputs": [],
"source": [
- "# Enter 'none', '0-1', or 'log' as achoice for data nomralization\n",
+ "# Enter 'none', '0-1', or 'log' as a choice for data nomralization\n",
"Data_Normalization_Choice = 'none'"
]
},
@@ -274,6 +274,86 @@
" print(clusterpoints[:,0],clusterpoints[:,1])\n"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Separating the Clusters for 2d Histograms"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# must run\n",
+ "\n",
+ "# creates dataset of ReqMemCPU, Elapsed, and AllocCPUS using the parameters in the labels shown above\n",
+ "\n",
+ "#Purple\n",
+ "df_purple = df_clustering[kmeans_cluster.labels_ == 0]\n",
+ "\n",
+ "#Green\n",
+ "df_green = df_clustering[kmeans_cluster.labels_ == 1]\n",
+ "\n",
+ "#Red\n",
+ "df_red = df_clustering[kmeans_cluster.labels_ == 2]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# voluntary\n",
+ "\n",
+ "# returns the min and max ReqMemCPU, Elapsed, and AllocCPUS for each cluster using the datasets created above. \n",
+ "# These are the parameters for the scatter plots of each cluster\n",
+ "print(\"Purple Cluster\")\n",
+ "print(\"ReqMemCPU:\", \"min =\",df_purple.ReqMemCPU.min(),\" \",\"max =\",df_purple.ReqMemCPU.max())\n",
+ "print(\"Elapsed:\", \"min =\",df_purple.Elapsed.min(),\" \",\"max =\",df_purple.Elapsed.max())\n",
+ "print(\"AllocCPUS:\", \"min =\",df_purple.AllocCPUS.min(),\" \",\"max =\",df_purple.AllocCPUS.max())\n",
+ "\n",
+ "print(\"\\nGreen Cluster\")\n",
+ "print(\"ReqMemCPU:\", \"min =\",df_green.ReqMemCPU.min(),\" \",\"max =\",df_green.ReqMemCPU.max())\n",
+ "print(\"Elapsed:\", \"min =\",df_green.Elapsed.min(),\" \",\"max =\",df_green.Elapsed.max())\n",
+ "print(\"AllocCPUS:\", \"min =\",df_green.AllocCPUS.min(),\" \",\"max =\",df_green.AllocCPUS.max())\n",
+ "\n",
+ "print(\"\\nRed Cluster\")\n",
+ "print(\"ReqMemCPU:\", \"min =\",df_red.ReqMemCPU.min(),\" \",\"max =\",df_red.ReqMemCPU.max())\n",
+ "print(\"Elapsed:\", \"min =\",df_red.Elapsed.min(),\" \",\"max =\",df_red.Elapsed.max())\n",
+ "print(\"AllocCPUS:\", \"min =\",df_red.AllocCPUS.min(),\" \",\"max =\",df_red.AllocCPUS.max())"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# must run\n",
+ "\n",
+ "# Creates datasets used to make the 2d histograms that correspond to each cluster scatter plot. \n",
+ "# The groupby does not change the data, but it does make a small enough dataset\n",
+ "\n",
+ "# for purple cluster \n",
+ "df_purlple_2d1 = df_purple.groupby(['ReqMemCPU','Elapsed']).sum().reset_index()\n",
+ "df_purlple_2d2 = df_purple.groupby(['AllocCPUS','Elapsed']).sum().reset_index()\n",
+ "df_purlple_2d3 = df_purple.groupby(['ReqMemCPU','AllocCPUS']).sum().reset_index()\n",
+ "\n",
+ "# for green cluster\n",
+ "df_green_2d1 = df_green.groupby(['ReqMemCPU','Elapsed']).sum().reset_index()\n",
+ "df_green_2d2 = df_green.groupby(['AllocCPUS','Elapsed']).sum().reset_index()\n",
+ "df_green_2d3 = df_green.groupby(['ReqMemCPU','AllocCPUS']).sum().reset_index()\n",
+ "\n",
+ "# for red cluster\n",
+ "df_red_2d1 = df_red.groupby(['ReqMemCPU','Elapsed']).sum().reset_index()\n",
+ "df_red_2d2 = df_red.groupby(['AllocCPUS','Elapsed']).sum().reset_index()\n",
+ "df_red_2d3 = df_red.groupby(['ReqMemCPU','AllocCPUS']).sum().reset_index()"
+ ]
+ },
{
"cell_type": "code",
"execution_count": null,
@@ -284,126 +364,267 @@
"\n",
"figure = plt.figure()\n",
"\n",
- "figure.set_size_inches(20,20)\n",
+ "figure.set_size_inches(20,40)\n",
+ "\n",
+ "# ReqMem/Elapsed 2d Graph\n",
+ "rqmem_elapsed_clustergraph = figure.add_subplot(5,3,1)\n",
"\n",
- "# Elapsed/ReqMem 2d Graph\n",
- "elapsed_rqmem_clustergraph = figure.add_subplot(3,3,1)\n",
- "#figure.suptitle('Runtime per Requested gigs of RAM %i gigs or less'%UpperlimitGB)\n",
- "elapsed_rqmem_clustergraph.scatter(df_clustering['ReqMemCPU'],df_clustering['Elapsed'], \n",
+ "rqmem_elapsed_clustergraph.scatter(df_clustering['ReqMemCPU'],df_clustering['Elapsed'], \n",
" c=kmeans_cluster.labels_, cmap='rainbow')\n",
- "elapsed_rqmem_clustergraph.scatter(clusterpoints[:,0] ,clusterpoints[:,1], color='black')\n",
+ "rqmem_elapsed_clustergraph.scatter(clusterpoints[:,0] ,clusterpoints[:,1], color='black')\n",
"plt.xlabel('ReqMemCPU(gigs)')\n",
"plt.ylabel('Elapsed(hours)')\n",
+ "plt.title('Runtime/Requested Gigs RAM')\n",
"\n",
"\n",
- "# Elapsed/Alloc 2d Graph\n",
- "elapsed_alloc_clustergraph = figure.add_subplot(3,3,2)\n",
- "#figure.suptitle('Runtime per Core %i cores or less'%UpperlimitAllocCPU)\n",
- "elapsed_alloc_clustergraph.scatter(df_clustering['AllocCPUS'],df_clustering['Elapsed'], \n",
+ "# Alloc/Elapsed 2d Graph\n",
+ "alloc_elapsed_clustergraph = figure.add_subplot(5,3,2)\n",
+ "alloc_elapsed_clustergraph.scatter(df_clustering['AllocCPUS'],df_clustering['Elapsed'], \n",
" c=kmeans_cluster.labels_, cmap='rainbow')\n",
- "elapsed_alloc_clustergraph.scatter(clusterpoints[:,2] ,clusterpoints[:,1], color='black')\n",
+ "alloc_elapsed_clustergraph.scatter(clusterpoints[:,2] ,clusterpoints[:,1], color='black')\n",
"plt.xlabel('AllocCPUS')\n",
"plt.ylabel('Elapsed(hours)')\n",
+ "plt.title('Runtime/Core')\n",
"\n",
- "# Alloc/ReqMem 2d Graph\n",
- "alloc_rqmem_clustergraph = figure.add_subplot(3,3,3)\n",
- "#figure.suptitle('Runtime per Requested gigs of RAM %i gigs or less'%UpperlimitGB)\n",
- "alloc_rqmem_clustergraph.scatter(df_clustering['ReqMemCPU'],df_clustering['AllocCPUS'], \n",
+ "# ReqMem/Alloc 2d Graph\n",
+ "rqmem_alloc_clustergraph = figure.add_subplot(5,3,3)\n",
+ "rqmem_alloc_clustergraph.scatter(df_clustering['ReqMemCPU'],df_clustering['AllocCPUS'], \n",
" c=kmeans_cluster.labels_, cmap='rainbow')\n",
- "elapsed_rqmem_clustergraph.scatter(clusterpoints[:,0] ,clusterpoints[:,2], color='black')\n",
+ "rqmem_alloc_clustergraph.scatter(clusterpoints[:,0] ,clusterpoints[:,2], color='black')\n",
"plt.xlabel('ReqMemCPU(gigs)')\n",
"plt.ylabel('AllocCPUS')\n",
+ "plt.title('Cores/Requested Gigs RAM')\n",
"\n",
- "###########\n",
- "# Alloc/ReqMem 3d Graph\n",
- "alloc_reqmem_clustergraph_3d = figure.add_subplot(3,3,4, projection='3d')\n",
- "alloc_reqmem_clustergraph_3d.scatter(df_clustering['ReqMemCPU'], df_clustering['AllocCPUS'], df_clustering['Elapsed'], \n",
+ "########### 3d Graphs\n",
+ "# ReqMem/Alloc 3d Graph\n",
+ "rqmem_alloc_clustergraph_3d = figure.add_subplot(5,3,4, projection='3d')\n",
+ "rqmem_alloc_clustergraph_3d.scatter(df_clustering['ReqMemCPU'], df_clustering['AllocCPUS'], df_clustering['Elapsed'], \n",
" c=kmeans_cluster.labels_ ,cmap='rainbow')\n",
- "alloc_reqmem_clustergraph_3d.scatter(clusterpoints[:,0] ,clusterpoints[:,2], color='black')\n",
- "alloc_reqmem_clustergraph_3d.set_xlabel('ReqMemCPU(gigs')\n",
- "alloc_reqmem_clustergraph_3d.set_ylabel('AllocCPUS')\n",
- "alloc_reqmem_clustergraph_3d.set_zlabel('Elapsed(hours)')\n",
+ "rqmem_alloc_clustergraph_3d.scatter(clusterpoints[:,0] ,clusterpoints[:,2], color='black')\n",
+ "rqmem_alloc_clustergraph_3d.set_xlabel('ReqMemCPU(gigs')\n",
+ "rqmem_alloc_clustergraph_3d.set_ylabel('AllocCPUS')\n",
+ "rqmem_alloc_clustergraph_3d.set_zlabel('Elapsed(hours)')\n",
"\n",
"# sets size and color for gridlines by axis\n",
- "alloc_reqmem_clustergraph_3d.xaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "alloc_reqmem_clustergraph_3d.yaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "alloc_reqmem_clustergraph_3d.zaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "rqmem_alloc_clustergraph_3d.xaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "rqmem_alloc_clustergraph_3d.yaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "rqmem_alloc_clustergraph_3d.zaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
"\n",
"\n",
- "# Elapsed/Alloc 3d Graph\n",
- "elapsed_alloc_clustergraph_3d = figure.add_subplot(3,3,5, projection='3d')\n",
- "elapsed_alloc_clustergraph_3d.scatter(df_clustering['AllocCPUS'], df_clustering['ReqMemCPU'], df_clustering['Elapsed'], \n",
+ "# Alloc/Elapsed 3d Graph\n",
+ "alloc_elapsed_clustergraph_3d = figure.add_subplot(5,3,5, projection='3d')\n",
+ "alloc_elapsed_clustergraph_3d.scatter(df_clustering['AllocCPUS'], df_clustering['ReqMemCPU'], df_clustering['Elapsed'], \n",
" c=kmeans_cluster.labels_ ,cmap='rainbow')\n",
- "elapsed_alloc_clustergraph_3d.scatter(clusterpoints[:,2] ,clusterpoints[:,1], color='black')\n",
- "elapsed_alloc_clustergraph_3d.set_xlabel('AllocCPUS')\n",
- "elapsed_alloc_clustergraph_3d.set_ylabel('ReqMemCPU(gigs)')\n",
- "elapsed_alloc_clustergraph_3d.set_zlabel('Elapsed(hours)')\n",
+ "alloc_elapsed_clustergraph_3d.scatter(clusterpoints[:,2] ,clusterpoints[:,1], color='black')\n",
+ "alloc_elapsed_clustergraph_3d.set_xlabel('AllocCPUS')\n",
+ "alloc_elapsed_clustergraph_3d.set_ylabel('ReqMemCPU(gigs)')\n",
+ "alloc_elapsed_clustergraph_3d.set_zlabel('Elapsed(hours)')\n",
"\n",
- "elapsed_alloc_clustergraph_3d.xaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "elapsed_alloc_clustergraph_3d.yaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "elapsed_alloc_clustergraph_3d.zaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "alloc_elapsed_clustergraph_3d.xaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "alloc_elapsed_clustergraph_3d.yaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "alloc_elapsed_clustergraph_3d.zaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
"\n",
"\n",
"\n",
- "# Elapsed/ReqMem 3d Graph\n",
- "elapsed_rqmem_clustergraph_3d = figure.add_subplot(3,3,6, projection='3d')\n",
- "elapsed_rqmem_clustergraph_3d.scatter(df_clustering['ReqMemCPU'], df_clustering['Elapsed'], df_clustering['AllocCPUS'], \n",
+ "# ReqMem/Elapsed 3d Graph\n",
+ "rqmem_elapsed_clustergraph_3d = figure.add_subplot(5,3,6, projection='3d')\n",
+ "rqmem_elapsed_clustergraph_3d.scatter(df_clustering['ReqMemCPU'], df_clustering['Elapsed'], df_clustering['AllocCPUS'], \n",
" c=kmeans_cluster.labels_ ,cmap='rainbow')\n",
- "elapsed_rqmem_clustergraph_3d.scatter(clusterpoints[:,0] ,clusterpoints[:,1], color='black')\n",
+ "rqmem_elapsed_clustergraph_3d.scatter(clusterpoints[:,0] ,clusterpoints[:,1], color='black')\n",
+ "\n",
+ "rqmem_elapsed_clustergraph_3d.set_xlabel('ReqMemCPU(gigs)')\n",
+ "rqmem_elapsed_clustergraph_3d.set_ylabel('Elapsed(hours)')\n",
+ "rqmem_elapsed_clustergraph_3d.set_zlabel('AllocCPUS')\n",
+ "\n",
+ "rqmem_elapsed_clustergraph_3d.xaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "rqmem_elapsed_clustergraph_3d.yaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "rqmem_elapsed_clustergraph_3d.zaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "\n",
+ "\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Creating bins \n",
+ "\n",
+ "####Purple\n",
+ "purple_rqmem_min = np.min(df_purple.ReqMemCPU.min())\n",
+ "purple_rqmem_max = np.max(df_purple.ReqMemCPU.max())\n",
+ " \n",
+ "purple_elapsed_min = np.min(df_purple.Elapsed.min()) \n",
+ "purple_elapsed_max = np.max(df_purple.Elapsed.max()) \n",
+ "\n",
+ "purple_alloc_min = np.min(df_purple.AllocCPUS.min()) \n",
+ "purple_alloc_max = np.max(df_purple.AllocCPUS.max())\n",
+ " \n",
+ " \n",
+ "x_purple_rqmem_elapsed_bins = list(range(purple_rqmem_max))\n",
+ "y_purple_rqmem_elapsed_bins = list(range(int(purple_elapsed_max)))\n",
"\n",
- "elapsed_rqmem_clustergraph_3d.set_xlabel('ReqMemCPU(gigs)')\n",
- "elapsed_rqmem_clustergraph_3d.set_ylabel('Elapsed(hours)')\n",
- "elapsed_rqmem_clustergraph_3d.set_zlabel('AllocCPUS')\n",
+ "x_purple_alloc_elapsed_bins = list(range(purple_alloc_max))\n",
+ "y_purple_alloc_elapsed_bins = list(range(int(purple_elapsed_max))) \n",
"\n",
- "elapsed_rqmem_clustergraph_3d.xaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "elapsed_rqmem_clustergraph_3d.yaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "elapsed_rqmem_clustergraph_3d.zaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "x_purple_reqmem_alloc_bins = list(range(purple_rqmem_max))\n",
+ "y_purple_reqmem_alloc_bins = list(range(int(purple_alloc_max))) \n",
"\n",
"\n",
- "##############\n",
- "# Alloc/ReqMem 3d Graph\n",
- "alloc_reqmem_clustergraph_3d = figure.add_subplot(3,3,7, projection='3d')\n",
- "alloc_reqmem_clustergraph_3d.scatter(df_clustering['ReqMemCPU'], df_clustering['AllocCPUS'], df_clustering['Elapsed'], \n",
- " c=kmeans_cluster.labels_ ,cmap='rainbow', alpha = .08)\n",
- "alloc_reqmem_clustergraph_3d.scatter(clusterpoints[:,0] ,clusterpoints[:,2], color='black')\n",
- "alloc_reqmem_clustergraph_3d.set_xlabel('ReqMemCPU(gigs')\n",
- "alloc_reqmem_clustergraph_3d.set_ylabel('AllocCPUS')\n",
- "alloc_reqmem_clustergraph_3d.set_zlabel('Elapsed(hours)')\n",
+ "####Green\n",
+ "green_rqmem_min = np.min(df_green.ReqMemCPU.min())\n",
+ "green_rqmem_max = np.max(df_green.ReqMemCPU.max())\n",
+ " \n",
+ "green_elapsed_min = np.min(df_green.Elapsed.min()) \n",
+ "green_elapsed_max = np.max(df_green.Elapsed.max()) \n",
"\n",
- "# sets size and color for gridlines by axis\n",
- "alloc_reqmem_clustergraph_3d.xaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "alloc_reqmem_clustergraph_3d.yaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "alloc_reqmem_clustergraph_3d.zaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
+ "green_alloc_min = np.min(df_green.AllocCPUS.min()) \n",
+ "green_alloc_max = np.max(df_green.AllocCPUS.max())\n",
+ " \n",
+ " \n",
+ "x_green_rqmem_elapsed_bins = list(range(green_rqmem_max))\n",
+ "y_green_rqmem_elapsed_bins = list(range(int(green_elapsed_max)))\n",
"\n",
+ "x_green_alloc_elapsed_bins = list(range(green_alloc_max))\n",
+ "y_green_alloc_elapsed_bins = list(range(int(green_elapsed_max))) \n",
"\n",
- "# Elapsed/Alloc 3d Graph\n",
- "elapsed_alloc_clustergraph_3d = figure.add_subplot(3,3,8, projection='3d')\n",
- "elapsed_alloc_clustergraph_3d.scatter(df_clustering['AllocCPUS'], df_clustering['ReqMemCPU'], df_clustering['Elapsed'], \n",
- " c=kmeans_cluster.labels_ ,cmap='rainbow', alpha = .08)\n",
- "elapsed_alloc_clustergraph_3d.scatter(clusterpoints[:,2] ,clusterpoints[:,1], color='black')\n",
- "elapsed_alloc_clustergraph_3d.set_xlabel('AllocCPUS')\n",
- "elapsed_alloc_clustergraph_3d.set_ylabel('ReqMemCPU(gigs)')\n",
- "elapsed_alloc_clustergraph_3d.set_zlabel('Elapsed(hours)')\n",
+ "x_green_reqmem_alloc_bins = list(range(green_rqmem_max))\n",
+ "y_green_reqmem_alloc_bins = list(range(int(green_alloc_max))) \n",
"\n",
- "elapsed_alloc_clustergraph_3d.xaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "elapsed_alloc_clustergraph_3d.yaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "elapsed_alloc_clustergraph_3d.zaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
"\n",
+ "####Red\n",
+ "red_rqmem_min = np.min(df_red.ReqMemCPU.min())\n",
+ "red_rqmem_max = np.max(df_red.ReqMemCPU.max())\n",
+ " \n",
+ "red_elapsed_min = np.min(df_red.Elapsed.min()) \n",
+ "red_elapsed_max = np.max(df_red.Elapsed.max()) \n",
"\n",
+ "red_alloc_min = np.min(df_red.AllocCPUS.min()) \n",
+ "red_alloc_max = np.max(df_red.AllocCPUS.max())\n",
+ " \n",
+ " \n",
+ "x_red_rqmem_elapsed_bins = list(range(red_rqmem_max))\n",
+ "y_red_rqmem_elapsed_bins = list(range(int (red_elapsed_max)))\n",
"\n",
- "# Elapsed/ReqMem 3d Graph\n",
- "elapsed_rqmem_clustergraph_3d = figure.add_subplot(3,3,9, projection='3d')\n",
- "elapsed_rqmem_clustergraph_3d.scatter(df_clustering['ReqMemCPU'], df_clustering['Elapsed'], df_clustering['AllocCPUS'], \n",
- " c=kmeans_cluster.labels_ ,cmap='rainbow', alpha = .08)\n",
- "elapsed_rqmem_clustergraph_3d.scatter(clusterpoints[:,0] ,clusterpoints[:,1], color='black')\n",
+ "x_red_alloc_elapsed_bins = list(range(red_alloc_max))\n",
+ "y_red_alloc_elapsed_bins = list(range(int (red_elapsed_max)))\n",
"\n",
- "elapsed_rqmem_clustergraph_3d.set_xlabel('ReqMemCPU(gigs)')\n",
- "elapsed_rqmem_clustergraph_3d.set_ylabel('Elapsed(hours)')\n",
- "elapsed_rqmem_clustergraph_3d.set_zlabel('AllocCPUS')\n",
+ "x_red_reqmem_alloc_bins = list(range(red_rqmem_max)) # list range gives one bin per gig\n",
+ "y_red_reqmem_alloc_bins = list(range(red_alloc_max)) # list range gives one bin per cpu"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "fig = plt.figure()\n",
+ "fig.set_size_inches(20,20)\n",
+ "\n",
+ "#####Green\n",
+ "ax = fig.add_subplot(331)\n",
+ "rqmem_elapsed_green_hist = ax.hist2d(df_green_2d1['ReqMemCPU'],df_green_2d1['Elapsed'], \n",
+ " bins =[x_green_rqmem_elapsed_bins, y_green_rqmem_elapsed_bins], \n",
+ " cmap = plt.cm.Blues)\n",
+ "ax.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax.set_ylabel('Elapsed(hours)')\n",
+ "ax.set_title('Green Cluster')\n",
+ "ax.set_xlim(0,40)\n",
+ "ax.set_ylim(0,140)\n",
+ "\n",
+ "\n",
+ "ax2 = fig.add_subplot(332)\n",
+ "alloc_elapsed_green_hist = ax2.hist2d(df_green_2d2['AllocCPUS'],df_green_2d2['Elapsed'], \n",
+ " bins =[x_green_alloc_elapsed_bins, y_green_alloc_elapsed_bins],\n",
+ " cmap = plt.cm.Blues)\n",
+ "ax2.set_xlabel('AllocCPUS')\n",
+ "ax2.set_ylabel('Elapsed(hours)')\n",
+ "ax2.set_title('Green Cluster')\n",
+ "ax2.set_xlim(0,40)\n",
+ "ax2.set_ylim(0,140)\n",
+ "\n",
+ "\n",
+ "ax3 = fig.add_subplot(333)\n",
+ "reqmem_alloc_green_hist = ax3.hist2d(df_green_2d3['ReqMemCPU'],df_green_2d3['AllocCPUS'], \n",
+ " bins =[x_green_reqmem_alloc_bins, y_green_reqmem_alloc_bins],\n",
+ " cmap = plt.cm.Blues)\n",
+ "ax3.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax3.set_ylabel('AllocCPUS')\n",
+ "ax3.set_title('Green Cluster')\n",
+ "ax3.set_xlim(0,40)\n",
+ "ax3.set_ylim(0,140)\n",
+ "\n",
+ " \n",
+ "####Purple\n",
+ "ax4 = fig.add_subplot(334) # This represents a (3x3) grid (row x col) and we are plotting the (1) subplot. The last number increments row-wise.\n",
+ "rqmem_elapsed_purple_hist = ax4.hist2d(df_purlple_2d1['ReqMemCPU'],df_purlple_2d1['Elapsed'], \n",
+ " bins =[x_purple_rqmem_elapsed_bins, y_purple_rqmem_elapsed_bins], \n",
+ " cmap = plt.cm.Blues)\n",
+ "ax4.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax4.set_ylabel('Elapsed(hours)')\n",
+ "ax4.set_title('Purple Cluster')\n",
+ "ax4.set_xlim(0,40)\n",
+ "ax4.set_ylim(0,140)\n",
+ "\n",
+ "\n",
+ "ax5 = fig.add_subplot(335) # Second subplot\n",
+ "alloc_elapsed_purple_hist = ax5.hist2d(df_purlple_2d2['AllocCPUS'],df_purlple_2d2['Elapsed'], \n",
+ " bins =[x_purple_alloc_elapsed_bins, y_purple_alloc_elapsed_bins], \n",
+ " cmap = plt.cm.Blues)\n",
+ "ax5.set_xlabel('AllocCPUS')\n",
+ "ax5.set_ylabel('Elapsed(hours)')\n",
+ "ax5.set_title('Purple Cluster')\n",
+ "ax5.set_xlim(0,40)\n",
+ "ax5.set_ylim(0,140)\n",
+ "\n",
+ "\n",
+ "ax6 = fig.add_subplot(336)\n",
+ "reqmem_alloc_purple_hist = ax6.hist2d(df_purlple_2d3['ReqMemCPU'],df_purlple_2d3['AllocCPUS'], \n",
+ " bins =[x_purple_reqmem_alloc_bins, y_purple_reqmem_alloc_bins], \n",
+ " cmap = plt.cm.Blues) # use magma or\n",
+ "ax6.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax6.set_ylabel('AllocCPUS')\n",
+ "ax6.set_title('Purple Cluster')\n",
+ "ax6.set_xlim(0,40)\n",
+ "ax6.set_ylim(0,140)\n",
+ "\n",
+ "\n",
+ "#####Red\n",
+ "ax7 = fig.add_subplot(337)\n",
+ "rqmem_elapsed_red_hist = ax7.hist2d(df_red_2d1['ReqMemCPU'],df_red_2d1['Elapsed'], \n",
+ " bins =[x_red_rqmem_elapsed_bins, y_red_rqmem_elapsed_bins],\n",
+ " cmap = plt.cm.Blues)\n",
+ "ax7.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax7.set_ylabel('Elapsed(hours)')\n",
+ "ax7.set_title('Red Cluster')\n",
+ "ax7.set_xlim(0,40)\n",
+ "ax7.set_ylim(0,140)\n",
+ "\n",
+ "\n",
+ "ax8 = fig.add_subplot(338)\n",
+ "alloc_elapsed_red_hist = ax8.hist2d(df_red_2d2['AllocCPUS'],df_red_2d2['Elapsed'], \n",
+ " bins =[x_red_reqmem_alloc_bins, y_red_reqmem_alloc_bins],\n",
+ " cmap = plt.cm.Blues)\n",
+ "ax8.set_xlabel('AllocCPUS')\n",
+ "ax8.set_ylabel('Elapsed(hours)')\n",
+ "ax8.set_title('Red Cluster')\n",
+ "ax8.set_xlim(0,40)\n",
+ "ax8.set_ylim(0,140)\n",
+ "\n",
+ "\n",
+ "ax9 = fig.add_subplot(339)\n",
+ "reqmem_alloc_red_hist = ax9.hist2d(df_red_2d3['ReqMemCPU'],df_red_2d3['AllocCPUS'], \n",
+ " bins =[x_red_reqmem_alloc_bins, y_red_reqmem_alloc_bins],\n",
+ " cmap = plt.cm.Blues)\n",
+ "ax9.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax9.set_ylabel('AllocCPUS')\n",
+ "ax9.set_title('Red Cluster')\n",
+ "ax9.set_xlim(0,40)\n",
+ "ax9.set_ylim(0,140)\n",
"\n",
- "elapsed_rqmem_clustergraph_3d.xaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "elapsed_rqmem_clustergraph_3d.yaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
- "elapsed_rqmem_clustergraph_3d.zaxis._axinfo[\"grid\"].update({\"linewidth\":.5, \"color\" : \"black\"})\n",
"\n",
"\n",
"# sets the spacing\n",
@@ -411,6 +632,151 @@
"# left = space to the left\n",
"# wspace = padding on both sides of graphs\n",
"# hspace = padding on top and bottom of graphs\n",
+ "\n",
+ "figure.subplots_adjust(left=0.0, wspace=0.2, top=.92, hspace=0.3)\n",
+ "figure.suptitle('Clusters', fontsize=20)\n",
+ "\n",
+ "plt.show()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Creating bins \n",
+ "\n",
+ "#### Reqmem/Elapsed\n",
+ "x_rqmem_elapsed_min = np.min(LowerlimitGB)\n",
+ "x_rqmem_elapsed_max = np.max(UpperlimitGB)\n",
+ " \n",
+ "y_rqmem_elapsed_min = np.min(LowerlimitElapsed) \n",
+ "y_rqmem_elapsed_max = np.max(UpperlimitElapsed) \n",
+ " \n",
+ "x_rqmem_elapsed_bins = np.linspace(x_rqmem_elapsed_min, x_rqmem_elapsed_max, 50) \n",
+ "y_rqmem_elapsed_bins = np.linspace(y_rqmem_elapsed_min, y_rqmem_elapsed_max, 20) \n",
+ "\n",
+ "####Alloc/Elapsed\n",
+ "x_alloc_elapsed_min = np.min(LowerlimitAllocCPU)\n",
+ "x_alloc_elapsed_max = np.max(UpperlimitAllocCPU)\n",
+ " \n",
+ "y_alloc_elapsed_min = np.min(LowerlimitElapsed) \n",
+ "y_alloc_elapsed_max = np.max(UpperlimitElapsed)\n",
+ "\n",
+ "x_alloc_elapsed_bins = np.linspace(x_alloc_elapsed_min, x_alloc_elapsed_max, 50) \n",
+ "y_alloc_elapsed_bins = np.linspace(y_alloc_elapsed_min, y_alloc_elapsed_max, 20) \n",
+ "\n",
+ "\n",
+ "###Alloc/Reqmem\n",
+ "x_reqmem_alloc_min = np.min(LowerlimitGB)\n",
+ "x_reqmem_alloc_max = np.max(UpperlimitGB)\n",
+ " \n",
+ "y_reqmem_alloc_min = np.min(LowerlimitAllocCPU) \n",
+ "y_reqmem_alloc_max = np.max(UpperlimitAllocCPU)\n",
+ "\n",
+ "x_reqmem_alloc_bins = np.linspace(x_reqmem_alloc_min, x_reqmem_alloc_max, 50) \n",
+ "y_reqmem_alloc_bins = np.linspace(y_reqmem_alloc_min, y_reqmem_alloc_max, 20) \n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "fig = plt.figure()\n",
+ "fig.set_size_inches(20,20)\n",
+ " \n",
+ "####Purple\n",
+ "ax = fig.add_subplot(331) # This represents a (3x3) grid (row x col) and we are plotting the (1) subplot. The last number increments row-wise.\n",
+ "rqmem_elapsed_purple_hist = ax.hist2d(df_purlple_2d1['ReqMemCPU'],df_purlple_2d1['Elapsed'], \n",
+ " bins =[x_rqmem_elapsed_bins, y_rqmem_elapsed_bins], \n",
+ " cmap = plt.cm.Greys)\n",
+ "ax.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax.set_ylabel('Elapsed(hours)')\n",
+ "ax.set_title('Purple Cluster')\n",
+ "\n",
+ "\n",
+ "ax2 = fig.add_subplot(332) # Second subplot\n",
+ "alloc_elapsed_purple_hist = ax2.hist2d(df_purlple_2d2['AllocCPUS'],df_purlple_2d2['Elapsed'], \n",
+ " bins =[x_alloc_elapsed_bins, y_alloc_elapsed_bins], \n",
+ " cmap = plt.cm.Greys)\n",
+ "ax2.set_xlabel('AllocCPUS')\n",
+ "ax2.set_ylabel('Elapsed(hours)')\n",
+ "ax2.set_title('Purple Cluster')\n",
+ "\n",
+ "\n",
+ "ax3 = fig.add_subplot(333)\n",
+ "reqmem_alloc_purple_hist = ax3.hist2d(df_purlple_2d3['ReqMemCPU'],df_purlple_2d3['AllocCPUS'], \n",
+ " bins =[x_reqmem_alloc_bins, y_reqmem_alloc_bins], \n",
+ " cmap = plt.cm.Greys) # use magma or\n",
+ "ax3.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax3.set_ylabel('AllocCPUS')\n",
+ "ax3.set_title('Purple Cluster')\n",
+ "\n",
+ "\n",
+ "#####Green\n",
+ "ax4 = fig.add_subplot(334)\n",
+ "rqmem_elapsed_green_hist = ax4.hist2d(df_green_2d1['ReqMemCPU'],df_green_2d1['Elapsed'], \n",
+ " bins =[x_rqmem_elapsed_bins, y_rqmem_elapsed_bins], \n",
+ " cmap = plt.cm.Greys)\n",
+ "ax4.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax4.set_ylabel('Elapsed(hours)')\n",
+ "ax4.set_title('Green Cluster')\n",
+ "\n",
+ "\n",
+ "ax5 = fig.add_subplot(335)\n",
+ "alloc_elapsed_green_hist = ax5.hist2d(df_green_2d2['AllocCPUS'],df_green_2d2['Elapsed'], \n",
+ " bins =[x_alloc_elapsed_bins, y_alloc_elapsed_bins],\n",
+ " cmap = plt.cm.Greys)\n",
+ "ax5.set_xlabel('AllocCPUS')\n",
+ "ax5.set_ylabel('Elapsed(hours)')\n",
+ "ax5.set_title('Green Cluster')\n",
+ "\n",
+ "\n",
+ "ax6 = fig.add_subplot(336)\n",
+ "reqmem_alloc_green_hist = ax6.hist2d(df_green_2d3['ReqMemCPU'],df_green_2d3['AllocCPUS'], \n",
+ " bins =[x_reqmem_alloc_bins, y_reqmem_alloc_bins],\n",
+ " cmap = plt.cm.Greys)\n",
+ "ax6.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax6.set_ylabel('AllocCPUS')\n",
+ "ax6.set_title('Green Cluster')\n",
+ "\n",
+ "\n",
+ "#####Red\n",
+ "ax7 = fig.add_subplot(337)\n",
+ "rqmem_elapsed_red_hist = ax7.hist2d(df_red_2d1['ReqMemCPU'],df_red_2d1['Elapsed'], \n",
+ " bins =[x_rqmem_elapsed_bins, y_rqmem_elapsed_bins],\n",
+ " cmap = plt.cm.Greys)\n",
+ "ax7.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax7.set_ylabel('Elapsed(hours)')\n",
+ "ax7.set_title('Red Cluster')\n",
+ "\n",
+ "\n",
+ "ax8 = fig.add_subplot(338)\n",
+ "alloc_elapsed_red_hist = ax8.hist2d(df_red_2d2['AllocCPUS'],df_red_2d2['Elapsed'], \n",
+ " bins =[x_reqmem_alloc_bins, y_reqmem_alloc_bins],\n",
+ " cmap = plt.cm.Greys)\n",
+ "ax8.set_xlabel('AllocCPUS')\n",
+ "ax8.set_ylabel('Elapsed(hours)')\n",
+ "ax8.set_title('Red Cluster')\n",
+ "\n",
+ "\n",
+ "ax9 = fig.add_subplot(339)\n",
+ "reqmem_alloc_red_hist = ax9.hist2d(df_red_2d3['ReqMemCPU'],df_red_2d3['AllocCPUS'], \n",
+ " bins =[x_reqmem_alloc_bins, y_reqmem_alloc_bins],\n",
+ " cmap = plt.cm.Greys)\n",
+ "ax9.set_xlabel('ReqMemCPU(gigs)')\n",
+ "ax9.set_ylabel('AllocCPUS')\n",
+ "ax9.set_title('Red Cluster')\n",
+ "\n",
+ "# sets the spacing\n",
+ "# top = space between title and graphs - increase number to bring title down and decrease to bring title up\n",
+ "# left = space to the left\n",
+ "# wspace = padding on both sides of graphs\n",
+ "# hspace = padding on top and bottom of graphs\n",
+ "\n",
"figure.subplots_adjust(left=0.0, wspace=0.2, top=.92, hspace=0.3)\n",
"figure.suptitle('Clusters', fontsize=20)\n",
"\n",