Add Pandas and Seaborn exercise files

Author: rlpitts

Exercises/day3/programs/pandas-ex1.py

@@ -0,0 +1,4 @@
+import pandas as pd
+
+df = pd.read_csv('exoplanets_5250_EarthUnits_fixed.csv',index_col=0)
+df.to_csv('./docs/day3/exoplanets_5250_EarthUnits.txt', sep='\t',index=True)

Exercises/day3/programs/pandas-ex2.py

@@ -0,0 +1,5 @@
+import numpy as np
+import pandas as pd
+
+df = pd.DataFrame( np.arange(1,13).reshape((4,3)), index=['w','x','y','z'], columns=['a','b','c'] )
+print(df)

Exercises/day3/programs/pandas-ex3.py

@@ -0,0 +1,9 @@
+import pandas as pd
+import numpy as np
+
+df = pd.read_csv('./docs/day3/exoplanets_5250_EarthUnits_fixed.csv',index_col=0)
+print("Before:\n", df['planet_type'].memory_usage(deep=True), '\n')
+
+# Convert planet_type to Categorical
+df['planet_type']=df['planet_type'].astype('category')
+print("After:\n", df['planet_type'].memory_usage(deep=True))

Exercises/day3/programs/pandas-ex4.py

@@ -0,0 +1,9 @@
+import pandas as pd
+import numpy as np
+
+loss_sum = 0
+for chunk in pd.read_csv('./docs/day3/global_disaster_response_2018-2024.csv',
+                         chunksize=10000):
+    loss_sum+=chunk['economic_loss_usd'].sum()
+print('total loss over all disasters in this database: $',
+      np.round(loss_sum/10**9,2), 'billion USD')  

Exercises/day3/programs/seaborn-ex1.py

@@ -0,0 +1,13 @@
+import seaborn as sb
+### Uncomment next 2 lines if running directly from cmd line:
+import matplotlib
+matplotlib.use("TkAgg")
+
+dat = sb.load_dataset('penguins')
+g = sb.pairplot(data=dat, corner=True, hue='species')
+### Use next 2 lines if running directly at cmd line
+g.figure.show()
+input("Press any key to exit")
+### comment line above, uncomment line below if running from batch script
+#g.figure.savefig('penguins_pairplot.png')
+### title and format file as desired

Exercises/day3/programs/seaborn-ex2.py

@@ -0,0 +1,14 @@
+import seaborn as sb
+from matplotlib import pyplot as plt
+### May need to uncomment next 2 lines if running directly from cmd line:
+#import matplotlib
+#matplotlib.use("TkAgg")
+
+mpg = sb.load_dataset('mpg')
+sb.clustermap(mpg.corr(numeric_only=True), annot=True, fmt=".2f",
+              cbar_kws={'label':'Correlation Coefficients'})
+### Use next line if copying to IDE or running directly at cmd line
+plt.show()
+### comment line above, uncomment line below if running from batch script
+#plt.savefig('mpg_clustermap',format='pdf')
+### title and format file as desired