import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

from statsmodels.tsa.stattools import adfuller
from statsmodels.tsa.seasonal import seasonal_decompose

import time
from tqdm import tqdm 
from scipy  import stats  
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

from sklearn.feature_selection import RFE
from sklearn.ensemble import ExtraTreesClassifier

from sklearn.metrics import f1_score
from sklearn.metrics import roc_auc_score
from sklearn.metrics import roc_curve, auc
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report

from xgboost import XGBClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression

df = pd.read_csv("sensor.csv")

print('here')

df.head()

# Find Duplicate Values
# Results will be the list of duplicate values
# If no duplicate values, nothing will list.
df[df['timestamp'].duplicated(keep=False)]

df.isnull().sum()

df['machine_status'].value_counts()

# Convert timestamp column into data type into datetime
df['timestamp'] = pd.to_datetime(df['timestamp'])

# Create a Series
time_period = pd.Series([])

# Assign values to series
for i in tqdm(range(df.shape[0])):
    if (df["timestamp"][i].hour >= 4) and (df[timestamp][i].hour < 10):
        time_period[i]="Morning"  
    elif (df["timestamp"][i].hour >= 10) and (df[timestamp][i].hour < 16):
        time_period[i]="Noon"  
    elif (df["timestamp"][i].hour >= 16) and (df[timestamp][i].hour < 22):   
        time_period[i]="Evening"
    else:    
        time_period[i]="Night"

# Insert new column time period
df.Insert(2, 'time_period', time_period)