Adding source code files for Chapter 6

2021-03-13 19:25:45 +04:00
parent e662762d09
commit 9589675a50
45 changed files with 625 additions and 0 deletions
@@ -0,0 +1,33 @@
+# pandastrick1.py
+import pandas as pd
+
+weekly_data = {'day':['Monday','Tuesday', 'Wednesday', 'Thursday',
+                      'Friday', 'Saturday', 'Sunday'],
+                'temp':[40, 33, 42, 31, 41, 40, 30],
+                'condition':['Sunny','Cloudy','Sunny','Rainy','Sunny',
+                        'Cloudy','Rainy']
+        }
+df = pd.DataFrame(weekly_data)
+
+#Replacing a numeric value of 40 with 39 across DF
+df.replace(40,39, inplace=True)
+
+#Replacing string Sunny with Sun across DF
+df.replace("Sunny","Sun",inplace=True)
+
+#Replacing strings starting with Cl with Cloud across DF
+df.replace(to_replace="^Cl.*",value="Cloud", inplace=True,regex=True)
+
+#Replacing Day names using a list across DF
+df.replace(["Monday","Tuesday"],["monday","tuesday"], inplace=True)
+
+#Replacing Day names using a single dict across DF
+df.replace({"Wednesday":"wednesday","Thursday":"thursday"}, inplace=True)
+
+#Replacing Day names using dict for column and value
+df.replace({"day":"Friday"}, {"day":"friday"}, inplace=True)
+
+#Replacing name of two days using dicts for column day
+df.replace({"day":{"Saturday":"saturday", "Sunday":"sunday"},
+            "condition":{"Rainy":"Rain"}}, inplace=True)
+print(df)
@@ -0,0 +1,17 @@
+# pandastrick2.py
+import pandas as pd
+
+weekly_data = {'day':['Monday','Tuesday', 'Wednesday', 'Thursday',
+                      'Friday', 'Saturday', 'Sunday'],
+                'temp':[40, 33, 42, 31, 41, 40, 30],
+                'condition':['Sunny,','_Cloudy ','Sunny','Rainy',
+                             '--Sunny.','Cloudy.','Rainy']
+        }
+df = pd.DataFrame(weekly_data)
+print(df)
+
+df["condition"] = df["condition"].map(
+                lambda x: x.lstrip('_- ').rstrip(',. '))
+
+df["temp_F"] = df["temp"].apply(lambda x: 9/5*x+32 )
+print(df)
@@ -0,0 +1,13 @@
+# pandastrick3.py
+import pandas as pd
+
+weekly_data = {'day':['Monday','Tuesday', 'Wednesday', 'Thursday',
+                      'Friday', 'Saturday', 'Sunday'],
+                'temp':[40, 33, 42, 31, 41, 40, 30],
+                'condition':['Sunny','Cloudy','Sunny','Rainy','Sunny',
+                        'Cloudy','Rainy']
+        }
+df = pd.DataFrame(weekly_data)
+
+print(df[(df.temp >= 30) & (df.temp<=40)])
+print(df[df.temp.between(30,40)])
@@ -0,0 +1,13 @@
+# pandastrick4.py
+import pandas as pd
+
+weekly_data = {'day':['Monday','Tuesday', 'Wednesday', 'Thursday',
+                      'Friday', 'Saturday', 'Sunday'],
+                'temp':[40, 33, 42, 31, 41, 40, 30],
+                'condition':['Sunny','Cloudy','Sunny','Rainy','Sunny',
+                        'Cloudy','Rainy']
+        }
+df = pd.DataFrame(weekly_data)
+
+print(df[(df.condition == 'Rainy') | (df.condition == 'Sunny')])
+print(df[df['condition'].str.contains('Rainy|Sunny')])
@@ -0,0 +1,17 @@
+# pandastrick5.py
+import pandas as pd
+import numpy as np
+pd.set_option('display.max_columns', None)
+
+weekly_data = {'day':['Monday','Tuesday', 'Wednesday', 'Thursday',
+                      'Friday', 'Saturday', 'Sunday'],
+                'temp':[40, 33, 42, 31, 41, 40, 30],
+                'condition':['Sunny','Cloudy','Sunny','Rainy','Sunny',
+                        'Cloudy','Rainy']
+        }
+df = pd.DataFrame(weekly_data)
+
+print(df.describe())
+print(df.describe(include="all"))
+print(df.describe(percentiles=np.arange(0, 1, 0.1)))
+print(df.groupby('condition').describe(percentiles=np.arange(0, 1, 0.1)))