import numpy as np 
import pandas as pd 

# csv 읽어오기/ 디렉토리 위치 넣어줌
import os 
print(os.listdir("./data"))

!pip install --upgrade pip

# !pip install scikit-learn

from IPython.display import Image
Image("C://Users/MyCom/jupyter-tutorial/kaggle/Womens Clothing E-Commerce Reviews/data/20211012_182601_1.png")

! pip install mplot3d-dragger

from mpl_toolkits.mplot3d import Axes3D # 3D matplotlib 라이브러리

from sklearn.preprocessing import StandardScaler
#StandardScaler
#1.각 특성의 평균을 0,분산을 1로 변경

#2.최솟값과 최댓값의 크기를 제한 하지 않는다.

import matplotlib.pyplot as plt
import seaborn as sns

import numpy as np
import os 
import pandas as pd 

print(os.listdir("./data"))

def plotPerColumnDistribution(df, nGraphShown, nGraphPerRow):
    nunique = df.nunique() # 데이터에 고유값들의 수를 출력해주는 함수
  
    # 고유값들의 수가 1과 50사이인 colunms들을 선택한다
    df = df[[col for col in df if nunique[col] > 1 and nunique[col] < 50]]
    
    nRow, nCol = df.shape
    columnNames = list(df)
    nGraphRow = (nCol + nGraphPerRow -1) / nGraphPerRow
    
    plt.figure(num = None, figsize = (6 * nGraphPerRow, 8 * nGraphRow), dpi = 80, facecolor = 'w', edgecolor = 'k')
    for i in range(min(nCol, nGraphShown)):
        plt.subplot(nGraphRow, nGraphPerRow, i + 1)
        columnDf = df.iloc[:, i]
        # issubdtype(arg1,arg2) 는 return으로 Boolean result 
        if (not np.issubdtype(type(columnDf.iloc[0]), np.number)):
            valueCounts = columnDf.value_counts()
            valueCounts.plot.bar()
        else:
            columnDf.hist()
        plt.ylabel('counts')
        plt.xticks(rotation = 90)
        plt.title(f'{columnNames[i]} (column {i})')
    plt.tight_layout(pad = 1.0, w_pad = 1.0, h_pad = 1.0)
    plt.show()

# Correlation matrix (상관관계 분석 시각화)
def plotCorrelationMatrix(df, graphWidth):
    filename = df.dataframeName
    df = df.dropna('columns') # drop columns with NaN
    df = df[[col for col in df if df[col].nunique() > 1]] # keep columns where there are more than 1 unique values
    if df.shape[1] < 2:
        print(f'No correlation plots shown: The number of non-NaN or constant columns ({df.shape[1]}) is less than 2')
        return
    corr = df.corr()
    plt.figure(num=None, figsize=(graphWidth, graphWidth), dpi=80, facecolor='w', edgecolor='k')
    corrMat = plt.matshow(corr, fignum = 1)
    plt.xticks(range(len(corr.columns)), corr.columns, rotation=90)
    plt.yticks(range(len(corr.columns)), corr.columns)
    plt.gca().xaxis.tick_bottom()
    plt.colorbar(corrMat)
    plt.title(f'Correlation Matrix for {filename}', fontsize=15)
    plt.show()

# Scatter and density plots
def plotScatterMatrix(df, plotSize, textSize):
    df = df.select_dtypes(include =[np.number]) # keep only numerical columns
    # Remove rows and columns that would lead to df being singular
    df = df.dropna('columns')
    df = df[[col for col in df if df[col].nunique() > 1]] # keep columns where there are more than 1 unique values
    columnNames = list(df)
    if len(columnNames) > 10: # reduce the number of columns for matrix inversion of kernel density plots
        columnNames = columnNames[:10]
    df = df[columnNames]
    ax = pd.plotting.scatter_matrix(df, alpha=0.75, figsize=[plotSize, plotSize], diagonal='kde')
    corrs = df.corr().values
    for i, j in zip(*plt.np.triu_indices_from(ax, k = 1)):
        ax[i, j].annotate('Corr. coef = %.3f' % corrs[i, j], (0.8, 0.2), xycoords='axes fraction', ha='center', va='center', size=textSize)
    plt.suptitle('Scatter and Density Plot')
    plt.show()

nRowsRead = 1000 # specify 'None' if want to read whole file
# Womens Clothing E-Commerce Reviews.csv has 23486 rows in reality, but we are only loading/previewing the first 1000 rows
df1 = pd.read_csv('./data/Womens Clothing E-Commerce Reviews.csv', delimiter=',', nrows = nRowsRead)
df1.dataframeName = 'Womens Clothing E-Commerce Reviews.csv'
nRow, nCol = df1.shape
print(f'There are {nRow} rows and {nCol} columns')

df1.head(5)

plotPerColumnDistribution(df1,10, 5)

plotCorrelationMatrix(df1, 8)

plotScatterMatrix(df1, 15,10)