Day 13 - drivendata blood donor prediction competition, code

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import cm as cm
from sklearn import tree, preprocessing
import sklearn.ensemble as ske
from sklearn.model_selection import train_test_split

df = pd.read_csv('train.csv')
def missing_values_table(df):
        mis_val = df.isnull().sum()
        mis_val_percent = 100 * df.isnull().sum() / len(df)
        mis_val_table = pd.concat([mis_val, mis_val_percent], axis=1)
        mis_val_table_ren_columns = mis_val_table.rename(
        columns = {0 : 'Missing Values', 1 : '% of Total Values'})
        mis_val_table_ren_columns = mis_val_table_ren_columns[
            mis_val_table_ren_columns.iloc[:,1] != 0].sort_values(
        '% of Total Values', ascending=False).round(1)
        print ("Your selected dataframe has " + str(df.shape[1]) + " columns.\n"      
            "There are " + str(mis_val_table_ren_columns.shape[0]) +
              " columns that have missing values.")
        return mis_val_table_ren_columns
    
df_m = missing_values_table(df)



def plot_corr(df,size=4):
    corr = df.corr()
    fig, ax = plt.subplots(figsize=(size, size))
    ax.matshow(corr,cmap=cm.Greys)
    plt.xticks(range(len(corr.columns)), corr.columns, rotation='vertical');
    plt.yticks(range(len(corr.columns)), corr.columns);
    plt.show()
    
    
plot_corr(df,10)

X = df.drop(['Made Donation in March 2007'], axis=1).values
y = df['Made Donation in March 2007'].values

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

clf_rf = ske.RandomForestClassifier(n_estimators=50)
clf_rf = clf_rf.fit(X_train, y_train)
print(clf_rf.score(X_test,y_test))

clf_gb = ske.GradientBoostingClassifier(n_estimators=50)
clf_gb = clf_gb.fit(X_train, y_train)
print(clf_gb.score(X_test,y_test))

importance = clf_gb.feature_importances_
print(importance)