vikramsoni2

from bayes_opt import BayesianOptimization
from sklearn.cross_validation import KFold
import xgboost as xgb

def xgbCv(train, features, numRounds, eta, gamma, maxDepth, minChildWeight, subsample, colSample):   
   # prepare xgb parameters 
   params = {
            "objective": "reg:linear",
            "booster" : "gbtree",
            "eval_metric": "mae",            

vikramsoni2

def plot_auc_pr(y_test, y_pred):
    
    fig = plt.figure(figsize=(20,7))

    plt.subplot(1,2,1)
    fpr, tpr, _ = roc_curve(y_test, y_pred)
    auc = roc_auc_score(y_test, y_pred)
    plt.plot(fpr,tpr,label="auc="+str(auc))
    plt.title('roc-auc curve')
    plt.legend(loc=4)

vikramsoni2

imp = pd.DataFrame({'feats':predictors,
                    'ranks': clf.feature_importances_}).sort_values('ranks', ascending=False)

fig, ax = plt.subplots(figsize=(12, 15))

# Example data
features = np.arange(len(imp.feats))
ranking = imp.ranks

ax.barh(features, ranking,  align='center', color='skyblue', ecolor='black')

vikramsoni2

import pandas as pd;
import numpy as np;
import lightgbm as lgb
from bayes_opt import BayesianOptimization
from sklearn.model_selection import cross_val_score

def lgb_evaluate(                
                numLeaves,
                maxDepth,
                scaleWeight,

vikramsoni2

from bayes_opt import BayesianOptimization
from sklearn.cross_validation import KFold
import xgboost as xgb
import numpy

def xgbCv(train, features, numRounds, eta, gamma, maxDepth, minChildWeight, subsample, colSample):
    # prepare xgb parameters 
    params = {
        "objective": "binary:logistic",
        "booster" : "gbtree",

vikramsoni2

features = ['bedrooms', 'bathrooms', 'sqft_living',
            'sqft_lot', 'floors', 'waterfront', 'view', 'condition', 'grade',
            'sqft_above', 'sqft_basement', 'yr_built', 'yr_renovated', 'zipcode',
            'sqft_living15', 'sqft_lot15']

f, ax = plt.subplots(figsize=(16, 12))
plt.title('Pearson Correlation Matrix',fontsize=25)

sns.heatmap(df[features].corr(), linewidths=0.25, vmax=1.0, square=True, cmap="BuGn_r", linecolor='k', annot=True)

vikramsoni2

{0: 'tench, Tinca tinca',
 1: 'goldfish, Carassius auratus',
 2: 'great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias',
 3: 'tiger shark, Galeocerdo cuvieri',
 4: 'hammerhead, hammerhead shark',
 5: 'electric ray, crampfish, numbfish, torpedo',
 6: 'stingray',
 7: 'cock',
 8: 'hen',
 9: 'ostrich, Struthio camelus',

vikramsoni2

def add_datepart(df, fldname, drop=True):
    fld = df[fldname]
    if not np.issubdtype(fld.dtype, np.datetime64):
        df[fldname] = fld = pd.to_datetime(fld, infer_datetime_format=True)
    targ_pre = re.sub('[Dd]ate$', '', fldname)
    for n in ('Year', 'Month', 'Week', 'Day', 'Dayofweek', 'Dayofyear',
            'Is_month_end', 'Is_month_start', 'Is_quarter_end', 'Is_quarter_start', 'Is_year_end', 'Is_year_start'):
        df[targ_pre+n] = getattr(fld.dt,n.lower())
    df[targ_pre+'Elapsed'] = fld.astype(np.int64) // 10**9
    if drop: df.drop(fldname, axis=1, inplace=True)

vikramsoni2

import optuna
from collections import Counter
# optuna 

predictors, target, key_id, entity, timestamp, order_by_entity, group_within_entity =  build_predictors_naming_conventions(list(df_train.columns.values))

def get_pos_weight(train, label=target):
    w = Counter(train[label])
    return round((w[0]/w[1])*0.90,2)

vikramsoni2

### Fuzzy matching between two arrays.
### for each item in array1, selects the most similar item from array2

import re, math
from collections import Counter

WORD = re.compile(r'\w+')

def get_cosine(vec1, vec2):
    intersection = set(vec1.keys()) & set(vec2.keys())