def predict(extract_fun):
"""
对结果进行预测
:param extract_fun:
:return:
"""
conn = get_conn()
cursor = conn.cursor()
# 恢复模型
clf = joblib.load("model_" + extract_fun.__name__ + ".pkl")
# 二分网络
graph = init_graph()
print("构建二分网络完成")
print(time.time())
# 进行投影
v_nodes = get_v_nodes()
a_nodes = get_a_nodes()
prjv_graph = project(graph, v_nodes)
prja_graph = project(graph, a_nodes)
print("投影完成")
print(time.time())
sql = "select * from public.ml_test_set"
cursor.execute(sql)
rows = cursor.fetchall()
f = open("predict_" + extract_fun.__name__ + ".txt", "w", encoding="utf-8")
for row in rows:
user_id = VName(row[0])
att_id = AName(row[1])
is_link = row[4]
if extract_fun.__name__ == "extract_direct":
feature = extract_direct(graph, user_id, att_id)
elif extract_fun.__name__ == "extract_indirect":
feature = extract_indirect(graph, prjv_graph, prja_graph, user_id,
att_id)
result = clf.predict([feature])[0]
f.writelines("%s\t%s\t%s\t%s\n" % (user_id, att_id, is_link, result))
f.close()
cursor.close()
conn.close()
def init_graph():
conn = get_conn()
cursor = conn.cursor()
graph = networkx.Graph()
# 添加 游客节点
VNodes = get_v_nodes()
for node in VNodes:
graph.add_node(node, bipartite=0)
# 添加景点节点
ANodes = get_a_nodes()
for node in ANodes:
graph.add_node(node, bipartite=1)
sql = "select * from public.train_set"
cursor.execute(sql)
rows = cursor.fetchall()
for row in rows:
user_id = row[7]
classroute = row[2]
classroutestr = row[3]
for atrraction_id in classroute:
if (VName(user_id), AName(atrraction_id)) in graph.edges:
graph[VName(user_id)][AName(atrraction_id)]["weight"] += 1
else:
graph.add_edge(VName(user_id), AName(atrraction_id), weight=1)
sql = "select * from public.test_set"
cursor.execute(sql)
rows = cursor.fetchall()
for row in rows:
user_id = row[7]
classroute = row[2]
classroutestr = row[3]
for atrraction_id in classroute[:-1]:
if (VName(user_id), AName(atrraction_id)) in graph.edges:
graph[VName(user_id)][AName(atrraction_id)]["weight"] += 1
else:
graph.add_edge(VName(user_id), AName(atrraction_id), weight=1)
return graph
def train(extract_fun):
"""
训练模型
:param: extract_fun
:return:
"""
# 读取数据
conn = get_conn()
cursor = conn.cursor()
# 二分网络
graph = init_graph()
print("构建二分网络完成")
print(time.time())
# 进行投影
v_nodes = get_v_nodes()
a_nodes = get_a_nodes()
prjv_graph = project(graph, v_nodes)
prja_graph = project(graph, a_nodes)
print("网络投影完成")
print(time.time())
sql = "select * from public.ml_train_set"
cursor.execute(sql)
rows = cursor.fetchall()
print(len(rows))
# 保存训练数据
X_list = list()
Y_list = list()
i = 0
for row in rows:
user_id = VName(row[0])
att_id = AName(row[1])
i += 1
print(i)
# print(time.time())
if extract_fun.__name__ == "extract_direct":
feature = extract_direct(graph, user_id, att_id)
elif extract_fun.__name__ == "extract_indirect":
feature = extract_indirect(graph, prjv_graph, prja_graph, user_id,
att_id)
# print(feature)
else:
print("wrong function")
break
X_list.append(feature)
if row[4]:
Y_list.append(1)
else:
Y_list.append(-1)
print("生成训练数据")
print(time.time())
cursor.close()
conn.close()
# 记录X_list， Y_list
f = open("param_" + extract_fun.__name__ + ".txt", "w", encoding="utf-8")
f.writelines(json.dumps(X_list) + "\n")
f.writelines(json.dumps(Y_list) + "\n")
f.close()
print("训练数据保存成功")
print(time.time())
clf = svm.SVC(kernel="linear")
clf.fit(X_list, Y_list)
print("训练数据结束")
print(time.time())
joblib.dump(clf, "model_" + extract_fun.__name__ + ".pkl")
print("保存模型")
print(time.time())
def recommend_test(extract_fun, tuned_params):
"""
根据GridSearchCV求得的参数 检验调参结果
:param tuned_params:
:return:
"""
conn = get_conn()
cursor = conn.cursor()
# 读数据
sql = "select * from public.ml_test_set"
cursor.execute(sql)
rows = cursor.fetchall()
# 构建模型
clf = svm.SVC(kernel=tuned_params["kernel"],
C=tuned_params["C"],
gamma=tuned_params["gamma"])
f = open("param_" + extract_fun.__name__ + ".txt", "r", encoding="utf-8")
x_list = f.readline()
x_list.split()
y_list = f.readline()
y_list.split()
f.close()
x_list = json.loads(x_list)
y_list = json.loads(y_list)
clf.fit(x_list, y_list)
# 二分网络
graph = init_graph()
print("构建二分网络完成")
print(time.time())
# 进行投影
v_nodes = get_v_nodes()
a_nodes = get_a_nodes()
prjv_graph = project(graph, v_nodes)
prja_graph = project(graph, a_nodes)
print("投影完成")
print(time.time())
# 所有的景点
a_nodes = list(get_node_id_dict().keys())
# 记录结果数据
f = open("recommend_" + extract_fun.__name__ + "_" +
tuned_params["kernel"] + "_C" + str(tuned_params["C"]) +
"_gamma" + str(tuned_params["gamma"]) + ".txt",
"w",
encoding="utf-8")
i = 0
for row in rows:
i += 1
print(i)
user_id = VName(row[0])
att_id = AName(row[1])
is_link = row[4]
if not is_link:
continue
sql = "select classroute from public.route_0320 where id={user_id}".format(
user_id=row[0])
cursor.execute(sql)
result = cursor.fetchone()
classroute = result[0]
# 待预测的集合
left_set = set(a_nodes) - set(classroute[0:-1])
recommendation = dict()
for anode in left_set:
anode = AName(anode)
if extract_fun.__name__ == "extract_direct":
feature = extract_direct(graph, user_id, anode)
elif extract_fun.__name__ == "extract_indirect":
feature = extract_indirect(graph, prjv_graph, prja_graph,
user_id, anode)
result = clf.predict([feature])[0]
dis = abs(clf.decision_function([feature]))
if result == 1:
recommendation[anode] = dis[0]
recommendation = dict(
sorted(recommendation.items(), key=lambda x: x[1], reverse=True))
f.write("%s\t%s\t%s\t%s\n" %
(user_id, classroute[:-1], att_id, json.dumps(recommendation)))
f.close()
cursor.close()
conn.close()
def recommend_list(extract_fun):
"""
利用之前生成的模型 进行推荐
:param extract_fun:
:return:
"""
conn = get_conn()
cursor = conn.cursor()
# 读数据
sql = "select * from public.ml_test_set"
cursor.execute(sql)
rows = cursor.fetchall()
# 读模型
clf = joblib.load("model_" + extract_fun.__name__ + ".pkl")
# 二分网络
graph = init_graph()
print("构建二分网络完成")
print(time.time())
# 进行投影
v_nodes = get_v_nodes()
a_nodes = get_a_nodes()
prjv_graph = project(graph, v_nodes)
prja_graph = project(graph, a_nodes)
print("投影完成")
print(time.time())
# 所有的景点
a_nodes = list(get_node_id_dict().keys())
# 记录结果数据
f = open("recommend_" + extract_fun.__name__ + ".txt",
"w",
encoding="utf-8")
for row in rows:
user_id = VName(row[0])
att_id = AName(row[1])
is_link = row[4]
if not is_link:
continue
sql = "select classroute from public.route_0320 where id={user_id}".format(
user_id=row[0])
cursor.execute(sql)
result = cursor.fetchone()
classroute = result[0]
# 待预测的集合
left_set = set(a_nodes) - set(classroute[0:-1])
recommendation = dict()
for anode in left_set:
anode = AName(anode)
if extract_fun.__name__ == "extract_direct":
feature = extract_direct(graph, user_id, anode)
elif extract_fun.__name__ == "extract_indirect":
feature = extract_indirect(graph, prjv_graph, prja_graph,
user_id, anode)
result = clf.predict([feature])[0]
dis = abs(clf.decision_function([feature]))
if result == 1:
recommendation[anode] = dis[0]
recommendation = dict(
sorted(recommendation.items(), key=lambda x: x[1], reverse=True))
f.write("%s\t%s\t%s\t%s\n" %
(user_id, classroute[:-1], att_id, json.dumps(recommendation)))
f.close()
cursor.close()
conn.close()
def write_train_feature(func, have_sd=0):
"""
生成训练集特征
并写入文件
:param func:
:param have_sd: 间接特征 是否含有最短距离
:return:
"""
if have_sd:
file_name = func.__name__ + "_has_sd_train.csv"
else:
file_name = func.__name__ + "_train.csv"
# 读取数据
conn = get_conn()
cursor = conn.cursor()
# 二分网络
graph = init_graph()
print("构建二分网络完成")
print(time.time())
# 进行投影
v_nodes = get_v_nodes()
a_nodes = get_a_nodes()
prjv_graph = project(graph, v_nodes)
prja_graph = project(graph, a_nodes)
print("网络投影完成")
print(time.time())
sql = "select * from public.ml_train_set"
cursor.execute(sql)
rows = cursor.fetchall()
print("len_rows:" + str(len(rows)))
if func.__name__ == "extract_direct":
title = ["label", "snv", "sna", "cn", "jc", "aa", "pa", "sd"]
elif func.__name__ == "extract_indirect":
if have_sd:
title = [
"label", "snv", "sna", "cn", "jc", "aa", "pa", "sd", "prj_cnv",
"prj_cna", "prj_jcv", "prj_jca", "prj_aav", "prj_aaa",
"prj_pav", "prj_paa", "prj_sdv", "prj_sda"
]
else:
title = [
"label", "snv", "sna", "cn", "jc", "aa", "pa", "sd", "prj_cnv",
"prj_cna", "prj_jcv", "prj_jca", "prj_aav", "prj_aaa",
"prj_pav", "prj_paa"
]
else:
print("函数错误")
return
i = 0
train_f = []
for row in rows:
i += 1
print(i)
user_id = VName(row[0])
att_id = AName(row[1])
if func.__name__ == "extract_direct":
feature = func(graph, user_id, att_id)
elif func.__name__ == "extract_indirect":
feature = func(graph, prjv_graph, prja_graph, user_id, att_id,
have_sd)
else:
print("函数错误")
if row[4]:
line = [1]
line.extend(feature)
train_f.append(line)
else:
line = [0]
line.extend(feature)
train_f.append(line)
# 写入到csv文件中
df = pd.DataFrame(train_f, columns=title)
df.to_csv(file_name, encoding="utf-8")
print("训练特征保存完成")
def write_test_feature(func, has_sd=0):
"""
保存测试集的特征
:param func:
:return:
"""
conn = get_conn()
cursor = conn.cursor()
if has_sd:
file_name = func.__name__ + "_has_sd_test.csv"
else:
file_name = func.__name__ + "_test.csv"
if func.__name__ == "extract_direct":
title = ["anode", "snv", "sna", "cn", "jc", "aa", "pa", "sd"]
elif func.__name__ == "extract_indirect":
if has_sd:
title = [
"anode", "snv", "sna", "cn", "jc", "aa", "pa", "sd", "prj_cnv",
"prj_cna", "prj_jcv", "prj_jca", "prj_aav", "prj_aaa",
"prj_pav", "prj_paa", "prj_sdv", "prj_sda"
]
else:
title = [
"anode", "snv", "sna", "cn", "jc", "aa", "pa", "sd", "prj_cnv",
"prj_cna", "prj_jcv", "prj_jca", "prj_aav", "prj_aaa",
"prj_pav", "prj_paa"
]
else:
print("函数错误")
return
# 读数据
sql = "select * from public.ml_test_set"
cursor.execute(sql)
rows = cursor.fetchall()
# 二分网络
graph = init_graph()
print("构建二分网络完成")
print(time.time())
# 进行投影
v_nodes = get_v_nodes()
a_nodes = get_a_nodes()
prjv_graph = project(graph, v_nodes)
prja_graph = project(graph, a_nodes)
print("投影完成")
print(time.time())
# 所有的景点
a_nodes = list(get_node_id_dict().keys())
test_f = []
i = 0
for row in rows:
print(i)
i += 1
user_id = VName(row[0])
att_id = AName(row[1])
is_link = row[4]
if not is_link:
continue
sql = "select classroute from public.route_0320 where id={user_id}".format(
user_id=row[0])
cursor.execute(sql)
result = cursor.fetchone()
classroute = result[0]
# 待预测的集合
left_set = set(a_nodes) - set(classroute[0:-1])
for anode in left_set:
anode = AName(anode)
if func.__name__ == "extract_direct":
feature = func(graph, user_id, anode)
elif func.__name__ == "extract_indirect":
feature = func(graph, prjv_graph, prja_graph, user_id, anode,
has_sd)
else:
print("函数名错误")
line = [anode]
line.extend(feature)
test_f.append(line)
# 写入到csv文件中
df = pd.DataFrame(test_f, columns=title)
df.to_csv(file_name, encoding="utf-8")
print("测试特征保存完成")