Mastering Social Media Mining 1 - Python tools for data science

Machine learning

#################################################################################
# Chap01/demo_sklearn.py

#################################################################################

 from sklearn import datasets 

 from sklearn.cluster import Means 

 import matplotlib.pyplot as pet 

 if __name__ == '__main__': 

 # Load the data 

 iris = datasets.load_iris() 

 X = iris.data 

 petal_length = X[:, 2] 

 petal_width = X[:, 3] 

 true_labels = iris.target 

 # Apply KMeans clustering 

 estimator = KMeans(n_clusters=3) 

 estimator.fit(X) 

 predicted_labels = estimator.labels_ 

 # Color scheme definition: red, yellow and blue 

 color_scheme = ['r', 'y', 'b'] 

 # Markers definition: circle, "x" and "plus" 

 marker_list = ['o', 'x', '+'] 

 # Assign colors/markers to the predicted labels 

 colors_predicted_labels = [color_scheme [lab] for lab in predicted_labels] 

 markers_predicted = [marker_list[lab] for lab in predicted_labels] 

 # Assign colors/markers to the true labels 

 colors_true_labels = [color_scheme[lab] for lab in true_labels] 

 markers_true = [marker_list[lab] for lab in true_labels] 

 # Plot and save the two scatter plots 

 for x, y, c, m in zip(petal_width, petal_length, colors_predicted_labels, markers_predicted): plt.scatter(x, y, c=c, marker=m) 

plt.savefig('iris_clusters.png') 

for x, y, c, m in zip(petal_width, petal_length, colors_true_labels, markers_true): 

plt.scatter(x, y, c=c, marker=m) 

 plt.savefig('iris_true_labels.png') 

 print(iris.target_names) 

Natural language processing

#################################################################################

Social network analysis

pip install networks

#################################################################################

# Chap01/demo_networkx.py

 import networkx as nx 

from datetime import date time 

if __name__ == '__main__': 

g = nx.Graph() 

g.add_node("John", {'name': 'John', 'age': 25}) 

g.add_node("Peter", {'name': 'Peter', 'age': 35}) 

g.add_node("Mary", {'name': 'Mary', 'age': 31}) 

g.add_node("Lucy", {'name': 'Lucy', 'age': 19}) 

g.add_edge("John", "Mary", {'since': datetime.today()}) 

g.add_edge("John", "Peter", {'since': datetime(1990, 7, 30)}) 

g.add_edge("Mary", "Lucy", {'since': datetime(2010, 8, 10)}) 

print(g.nodes()) 

print(g.edges()) 

print(g.has_edge("Lucy", "Mary"))

Processing data in Python

#################################################################################

# Chap01/demo_json.py

import json 

if __name__ == '__main__': 

user_json = '{"user_id": "1", "name": "Marco"}' 

user_data = json.loads(user_json) 

print(user_data['name']) # Marco 

user_data['likes'] = ['Python', 'Data Mining'] 

user_json = json.dumps(user_data, indent=4) 

print(user_json)