Adding chapter 03 code.

Author: saberry

code/chapter_01_video_05.py

@@ -0,0 +1,14 @@
+import pandas as pd
+import requests
+
+base_link = 'https://pixelford.com/api/image/id/'
+
+pixelford_list = []
+
+for i in range(20):
+    individual_link = base_link + str(i)
+    initial_request = requests.get(individual_link)
+    json_results = initial_request.content
+    pixelford_list.append(pd.read_json(json_results))
+
+pixelford_list = pd.concat(pixelford_list)

code/chapter_03_video_02.py

@@ -0,0 +1,18 @@
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import seaborn as sns
+
+employees = pd.read_csv('data/level_up_data.csv')
+
+data_types = employees.dtypes
+
+numeric_columns = employees.columns[(data_types == 'float64') | (data_types == 'int64')]
+
+numeric_employees = employees[numeric_columns]
+
+numeric_employees = numeric_employees.drop('separated_ny', axis = 1)
+
+employee_correlations = numeric_employees.corr()
+
+print(employee_correlations)

code/chapter_03_video_03.py

@@ -0,0 +1,31 @@
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import seaborn as sns
+
+employees = pd.read_csv('data/level_up_data.csv')
+
+data_types = employees.dtypes
+
+numeric_columns = employees.columns[(data_types == 'float64') | (data_types == 'int64')]
+
+numeric_employees = employees[numeric_columns]
+
+numeric_employees = numeric_employees.drop('separated_ny', axis = 1)
+
+employee_correlations = numeric_employees.corr()
+
+employee_correlations
+
+mask = np.triu(np.ones_like(employee_correlations, dtype=bool))
+
+f, ax = plt.subplots(figsize=(6, 4))
+
+ax.set_xticklabels(ax.get_xticklabels(), rotation = 30)
+
+ax.set_yticklabels(ax.get_yticklabels(), rotation = 90)
+
+sns.heatmap(employee_correlations, mask=mask, cmap="YlGnBu", center=0)
+            
+plt.show()            
+

code/chapter_03_video_04.py

@@ -0,0 +1,31 @@
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import seaborn as sns
+
+employees = pd.read_csv('data/level_up_data.csv')
+
+employees.select_dtypes
+
+def z_score_maker(variable):
+  variable_mean = variable.mean()
+  variable_sd = variable.std()
+  z_score = (variable - variable_mean) / variable_sd 
+  return z_score
+
+viz_variables = ['prior_job_count', 'days_to_separate', 
+  'proportion_401K', 'starting_salary']
+
+for i in viz_variables:  
+  employees[i] = z_score_maker(employees[i])
+
+employees_melted = employees.melt(id_vars = 'department', 
+  value_vars = viz_variables)
+  
+g = sns.catplot(x="value", y="variable",
+                hue="department", 
+                data=employees_melted,
+                orient="h", height=2, aspect=3, palette="Set3",
+                kind="violin", dodge=True, cut=0, bw=.2, sharex=False)
+
+plt.show()