# 导入相应模块
import numpy as np 
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.font_manager import FontProperties
font = FontProperties(fname = "./input/SimHei.ttf", size=14)

import seaborn as sns
import random

# 设置绘图风格
%matplotlib inline
sns.set(style='whitegrid')

# 忽略所有警告
import warnings
warnings.filterwarnings('ignore')

# 读取数据
data = pd.read_csv('./input/african_crises.csv')
data.sample(5)

unique_countries = data.country.unique()
unique_countries

data.info()

data.describe(include = 'all')

data[data['currency_crises'] == 2]

data = data[data['currency_crises'] != 2]
data.shape

plt.figure(figsize=(12,20))


for i in range(13):
    
    plt.subplot(7,2,i+1)
    country = unique_countries[i]
    
    # 随机生成一种颜色 random.choice():从一个序列中随机的抽取一个元素，抽取6次组成6位代表随机颜色
    col="#"+''.join([random.choice('0123456789ABCDEF') for j in range(6)])
    
    sns.lineplot(data[data.country == country]['year'],data[data.country == country]['exch_usd'],label = country,color = col)
    
    # np.logical_and()逻辑与 两个条件均成立时返回True
    plt.plot([np.min(data[np.logical_and(data.country == country,data.independence == 1)]['year']),
              np.min(data[np.logical_and(data.country == country,data.independence == 1)]['year'])],
             [0,np.max(data[data.country == country]['exch_usd'])],color = 'black',linestyle = 'dotted',alpha = 0.8)
    

    plt.title(country)
    
plt.tight_layout()
plt.show()

plt.figure(figsize=(12,20))


for i in range(13):
    
    plt.subplot(7,2,i+1)
    country = unique_countries[i]
    
    # 随机生成一种颜色
    col="#"+''.join([random.choice('0123456789ABCDEF') for j in range(6)])
    
    sns.lineplot(data[data.country == country]['year'],data[data.country == country]['inflation_annual_cpi'],label = country,color = col)
    
    plt.scatter(data[data.country == country]['year'],data[data.country == country]['inflation_annual_cpi'],color = col,s = 28)
    
    plt.plot([np.min(data[np.logical_and(data.country == country,data.independence==1)]['year']),
              np.min(data[np.logical_and(data.country == country,data.independence==1)]['year'])],
             [np.min(data[data.country == country]['inflation_annual_cpi']),np.max(data[data.country == country]['inflation_annual_cpi'])],
             color = 'black',linestyle = 'dotted',alpha = 0.8)

    plt.title(country)
    
plt.tight_layout()
plt.show()

sns.set(style='darkgrid')
columns = ['systemic_crisis','domestic_debt_in_default','sovereign_external_debt_default','currency_crises','inflation_crises','banking_crisis']

plt.figure(figsize=(16,16))

for i in range(6):
    plt.subplot('32'+str(i+1))
    sns.countplot(y = data.country,hue = data[columns[i]],palette = 'rocket')
    plt.legend(loc = 0)
    plt.title(columns[i])
    
plt.tight_layout()
plt.show()

systemic = data[['year','country', 'systemic_crisis', 'exch_usd', 'banking_crisis']]
systemic = systemic[(systemic['country'] == 'Central African Republic') | (systemic['country']=='Kenya') | (systemic['country']=='Zimbabwe') ]
plt.figure(figsize=(12,12))
count = 1

for country in systemic.country.unique():
    plt.subplot(len(systemic.country.unique()),1,count)
    subset = systemic[(systemic['country'] == country)]
    sns.lineplot(subset['year'],subset['systemic_crisis'],ci=None)
    plt.scatter(subset['year'],subset["banking_crisis"], color='coral', label='Banking Crisis')
    plt.subplots_adjust(hspace=0.6)
    plt.xlabel('Years')
    plt.ylabel('Systemic Crisis/Banking Crisis')
    plt.title(country)
    count+=1

data['banking_crisis'] = data['banking_crisis'].map({"no_crisis":0,"crisis":1})

selected_features = ['systemic_crisis', 'exch_usd', 'domestic_debt_in_default','sovereign_external_debt_default', 'gdp_weighted_default',
       'inflation_annual_cpi', 'independence', 'currency_crises','inflation_crises','banking_crisis']

corr = data[selected_features].corr()

fig = plt.figure(figsize = (12,8))

cmap = sns.diverging_palette(220, 10, as_cmap=True)
mask = np.zeros_like(corr, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True

# 绘制热力图
sns.heatmap(corr, mask=mask, cmap=cmap,vmin=-0.5,vmax=0.7, center=0,annot = True,
            square=True, linewidths=.5,cbar_kws={"shrink": .5});

plt.title("特征间的相关性",fontproperties = font)
plt.show()

data.drop(['case','cc3'],axis = 1,inplace = True)
data = pd.get_dummies(data = data,columns = ['country'])
data.head()

fig = plt.figure(figsize = (8,6))

data['banking_crisis'].value_counts().plot(kind='bar',rot = 360,color = 'lightseagreen')

plt.xticks([0,1],["no_crisis","crisis"])
plt.show()

from sklearn import model_selection

x = data.drop('banking_crisis',axis = 1)
y = data['banking_crisis']

x_train,x_test,y_train,y_test = model_selection.train_test_split(x, y,test_size=0.2,random_state = 33,stratify=y)

from imblearn.over_sampling import SMOTE
x_train_resampled, y_train_resampled = SMOTE(random_state=4).fit_sample(x_train, y_train)

print(x_train_resampled.shape, y_train_resampled.shape)

from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier(n_estimators = 100, max_depth = 20,max_features = 10, random_state = 20)
rf.fit(x_train_resampled, y_train_resampled)
y_pred = rf.predict(x_test)

from sklearn.metrics import classification_report,confusion_matrix

print(classification_report(y_test, y_pred))
confusion_matrix = confusion_matrix(y_test, y_pred)
print(confusion_matrix)

fig,ax = plt.subplots(figsize=(8,6))
sns.heatmap(confusion_matrix,ax=ax,annot=True,annot_kws={'size':15}, fmt='d',cmap = 'YlGnBu_r')
ax.set_ylabel('真实值',fontproperties = font)
ax.set_xlabel('预测值',fontproperties = font)
ax.set_title('混淆矩阵热力图',fontproperties = font)
plt.show()

from sklearn.metrics import roc_auc_score
from sklearn.metrics import roc_curve

roc_auc = roc_auc_score(y_test, rf.predict(x_test))
fpr, tpr, thresholds = roc_curve(y_test, rf.predict_proba(x_test)[:,1])

plt.figure(figsize = (8,6))

plt.plot(fpr, tpr, label='Random Forest (area = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1],'r--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC curve')

plt.legend(loc="lower right")
plt.show()

fig = plt.figure(figsize=(16,12))

rf_importance = rf.feature_importances_
index = data.drop(['banking_crisis'], axis=1).columns
rf_feature_importance = pd.DataFrame(rf_importance.T, index=index,columns=['score']).sort_values(by='score', ascending=True)

# 水平条形图绘制
rf_feature_importance.plot(kind='barh',legend=False,color = 'deepskyblue')

plt.title('随机森林特征重要性',fontproperties = font)

plt.show()