added seaborn plots and consolidated code lines

slurm-2sql.ipynb

 %% Cell type:code id: tags:
 
 ``` 
 import sqlite3
 import slurm2sql
 import pandas as pd
 import matplotlib.pyplot as plt
 %matplotlib inline
 import seaborn as sns
 import plotly.express as px
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 upperRAMlimit = 50e+10 # 5 gigs
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 # creates database of info from March 2020 using sqlite 3
 db = sqlite3.connect('/data/rc/rc-team/slurm-since-March.sqlite3')
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 # creates database of allocation info from March 2020 using sqlite 3
 # not using this right now, but is here as an option
 #db_allocation = sqlite3.connect('/data/rc/rc-team/slurm-since-March-allocation.sqlite3')
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 # df_1 is starting database
 df_1 = pd.read_sql('SELECT * FROM slurm', db)
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 # for displaying all available column options
 pd.set_option('display.max_columns', None)
 df_1.head(5)
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 # df_2 is database with only ReqMemCpu and ReqMemNode, and ArrayTaskID
 df_2 = df_1.loc[:,['JobName','ReqMemCPU', 'ReqMemNode', 'ArrayJobID','ArrayTaskID']]
 df_2.head(5)
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 # df_batch is df_2 with only batch jobs
 df_batch = df_1.JobName.str.contains('batch')
 df_2[df_batch]
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 # creates database from df_batch of ReqMemCPU batch jobs that are < or = a given point
 CPU_cutoff = df_2[df_batch][(df_2[df_batch].ReqMemCPU <= upperRAMlimit)]
-CPU_cutoff
+#CPU_cutoff
+Node_cutoff = df_2[df_batch][(df_2[df_batch].ReqMemNode <= upperRAMlimit)] # 1e+10 is 1 gig
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 # gives mean, min, max, std, and 3 percentiles for cutoff data
 # can change what to include or exclude
 CPU_cutoff.describe(include=None, exclude=None)
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
+# gives mean, min, max, std, and 3 percentiles for cutoff data
+# can change what to include or exclude
+Node_cutoff.describe(include=None, exclude=None)
+```
+
+%% Cell type:code id: tags:
+
+``` 
+CPU_fig = sns.distplot(CPU_cutoff['ReqMemCPU'],  kde=False, label='CPU', color = "green")
+CPU_fig.set_yscale('log')
+plt.legend(prop={'size': 12})
+plt.title('User Request of CPU')
+plt.xlabel('Requested Gigs')
+plt.ylabel('Amount of Users Requesting')
+```
+
+%% Cell type:code id: tags:
+
+``` 
+Node_fig = sns.distplot(Node_cutoff['ReqMemNode'],  kde=False, label='Node')
+Node_fig.set_yscale('log')
+
+plt.legend(prop={'size': 12})
+plt.title('User Request of Node')
+plt.xlabel('Requested Gigs')
+plt.ylabel('Amount of Users Requesting')
+```
+
+%% Cell type:code id: tags:
+
+``` 
+CPU_fig = sns.distplot(CPU_cutoff['ReqMemCPU'],  kde=False, label='CPU', color = "green")
+CPU_fig.set_yscale('log')
+
+Node_fig = sns.distplot(Node_cutoff['ReqMemNode'],  kde=False, label='Node') #color = 'darkblue')
+Node_fig.set_yscale('log')
+
+plt.legend(prop={'size': 12})
+plt.title('User Request of CPU and Node')
+plt.xlabel('Requested Gigs')
+plt.ylabel('Amount of Users Requesting')
+```
+
+%% Cell type:code id: tags:
+
+``` 
 # creates histogram of ReqMemCPU for the month of March 2020
 # uses cutoff cpu memory declared in CPU_cutoff - 1 gig
 # also can show box or violing graph above to show where min, max, median, and 3rd quartile is
 # the mean is at just under half a gig requested memory CPU
 
 CPU_fig = px.histogram(CPU_cutoff, x="ReqMemCPU",
                    title='Histogram of ReqMemCPU',
                    labels={'ReqMemCPU':'ReqMemCPU'}, # can specify one label per df column
                    opacity=0.8,
                    log_y=True, # represent bars with log scale
                    marginal="box", # can be `box`, `violin`
                    hover_data=CPU_cutoff.columns,
                    nbins=30,
                    color_discrete_sequence=['goldenrod'] # color of histogram bars
                    )
-CPU_fig.show()
-```
-
-%% Cell type:code id: tags:
-
-``` 
-# creates database from df_batch of ReqMemNode batch jobs that are < or = a given point
-Node_cutoff = df_2[df_batch][(df_2[df_batch].ReqMemNode <= upperRAMlimit)] # 1e+10 is 1 gig
+#CPU_fig.show()
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 # creates histogram of ReqMemNode for the month of March 2020
 # uses cutoff node memory declared in Node_cutoff - 1 gig
 # also can show box or violing graph above to show where min, max, median, and 3rd quartile is
 # the mean is at just under half a gig requested memory Node
 
 Node_fig = px.histogram(Node_cutoff, x="ReqMemNode",
                    title='Histogram of ReqMemNode',
                    labels={'ReqMemNode':'ReqMemNode'}, # can specify one label per df column
                    opacity=0.8,
                    log_y=True, # represent bars with log scale
                    marginal="box", # can be `box`, `violin`
                    hover_data=Node_cutoff.columns,
                    nbins=30,
                    color_discrete_sequence=['darkblue'] # color of histogram bars
                    )
-Node_fig.show()
+#Node_fig.show()
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
-# creates database from df_batch of ReqMemCPU batch jobs that are < or = a given point
-CPU_arraytask = CPU_cutoff.ArrayID != 'NaN')] # 1e+10 is 1 gig
+CPU_arraytask = CPU_cutoff.dropna(subset=['ArrayTaskID'])
 CPU_arraytask
 ```
 
 %% Cell type:code id: tags:
 
 ``` 
 ```