user_preference_predict/data_analysis_0213.py

import pandas as pd
from common.log_utils import logFactory
from common.database_utils import database_util
from common import constant
import pickle
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

click_client = database_util.get_client()
logger = logFactory("data analysis").log

if __name__:
    total_pos = pd.read_pickle("data_pos_2013.pkl")
    total_neg = pd.read_pickle("data_neg_2013.pkl")

    total_pos['mark'] = 0
    total_neg['mark'] = 1

    total_train_data = pd.concat([total_pos, total_neg], axis=0)

    t0 = total_train_data[['EVENT_CONSUM_V', 'mark']]
    t0 = t0[t0.EVENT_CONSUM_V <= 100]
    all_data = pd.melt(t0, id_vars='mark', var_name="Features",
                       value_name="Values")
    sns.violinplot(
        x="Features",
        y="Values",
        hue="mark",
        data=all_data,
        split=False,
        palette='muted'
    )
    plt.show()

    t1 = total_train_data[['EVENT_VIDEO_FLUX_V', 'mark']]
    t1 = t1[t1.EVENT_VIDEO_FLUX_V <= 50]
    all_data = pd.melt(t1, id_vars='mark', var_name="Features",
                       value_name="Values")
    sns.violinplot(
        x="Features",
        y="Values",
        hue="mark",
        data=all_data,
        split=False,
        palette='muted'
    )
    plt.show()