jenjenjiang

jenjenjiang

jenjenjiang

jenjenjiang

jenjenjiang

from os import path
import jieba
import jieba.analyse as ja
pip install jieba
from gensim.test.utils import common_texts, get_tmpfile

with open('../JJ/lyric.txt', 'r') as handle:
    print(handle)
    for line in handle:
        tags = ja.extract_tags(line, topK=10, withWeight=True)

jenjenjiang

# DecisionTreeClassifier predict 
from sklearn.metrics import accuracy_score
x_test = dev_test.iloc[:,0:46]
x_test_1 = x_test.drop(['Client_MYOL_Statut'], axis=1, inplace=False)
x_t1_m = x_test_1.as_matrix()
test_pred = clf.predict(x_t1_m)
y_test = dev_test.Client_Abo_1819.as_matrix()

jenjenjiang

#use Silhouette Analysis
from sklearn.metrics import silhouette_samples, silhouette_score
range_n_clusters = [2, 3, 4, 5, 6,7,8,9]
for n_clusters in range_n_clusters:
    kmeans = KMeans(n_clusters=n_clusters, random_state=0).fit(data_std)
    labels = kmeans.labels_
    silhouette_avg = silhouette_score(data_std, labels)
    print("For n_clusters =", n_clusters,
          "The average silhouette_score is :", silhouette_avg)

jenjenjiang

import pandas as pd
import numpy as np
import sys

def get_size(total_size, percentage, mean):
    size_train = int(percentage * total_size / 100)
    size_client_abo = [int(size_train * (1 - mean)), int(size_train * mean)] 
    return size_client_abo

def populate(data, indexs, sizes):

jenjenjiang

#1 Retrain the linear and polynomial models
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn import metrics
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import PolynomialFeatures
from sklearn.metrics import r2_score

X_train, X_test, y_train, y_test = train_test_split(
   X, Y, test_size=0.3, random_state=0)

jenjenjiang