Project 6

import numpy as np  
import pandas as pd
import tensorflow as tf
import matplotlib.pyplot as plt
import missingno as msno
import seaborn as sns
df=pd.read_csv('machine_failure_data.csv')
msno.matrix(df)

values_list = list()
cols_list = list()
for col in df.columns:
    pct_missing = np.mean(df[col].isnull())*100
    cols_list.append(col)
    values_list.append(pct_missing)
pct_missing_df = pd.DataFrame()
pct_missing_df['col'] = cols_list
pct_missing_df['pct_missing'] = values_list
pct_missing_df.loc[pct_missing_df.pct_missing > 0].plot(kind='bar', figsize=(12,8))
plt.show()

less_missing_values_cols_list = list(pct_missing_df.loc[(pct_missing_df.pct_missing < 0.5) & (pct_missing_df.pct_missing > 0), 'col'].values)
df.dropna(subset=less_missing_values_cols_list, inplace=True)

# dropping columns with more than 40% null values
_40_pct_missing_cols_list = list(pct_missing_df.loc[pct_missing_df.pct_missing > 40, 'col'].values)
df.drop(columns=_40_pct_missing_cols_list, inplace=True)


# select numerical columns
df_numeric = df.select_dtypes(['int64','float64'])
numeric_cols = df_numeric.columns.values
# select non-numeric columns
df_non_numeric =df.select_dtypes(['object'])
non_numeric_cols = df_non_numeric.columns.values

for col in numeric_cols:
    missing = df[col].isnull()
    num_missing = np.sum(missing)
    if num_missing > 0:  # impute values only for columns that have missing values
        med = df[col].median() #impute with the median
        df[col] = df[col].fillna(med)


for col in non_numeric_cols:
    missing = df[col].isnull()
    num_missing = np.sum(missing)
    if num_missing > 0:  # impute values only for columns that have missing values
        mod = df[col].describe()['top'] # impute with the most frequently occuring value
        df[col] = df[col].fillna(mod)

# dropping duplicates by considering all columns 
cols_other_than_id = list(df.columns)
df.drop_duplicates(subset=cols_other_than_id, inplace=True)
##
from sklearn.preprocessing import LabelEncoder
for col in non_numeric_cols:
    df[col] = LabelEncoder().fit_transform(df[col].values)
df.head()


X=df.drop('Fail_tomorrow',axis=1)
Y=df['Fail_tomorrow']
#Splitting dataset into training and testing dataset
from sklearn.model_selection import train_test_split
X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size=0.2,random_state=0)


#Performing Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

#Initialising ANN
ann = tf.keras.models.Sequential()
#Adding First Hidden Layer
ann.add(tf.keras.layers.Dense(units=6,activation="relu"))
#Adding Second Hidden Layer
ann.add(tf.keras.layers.Dense(units=6,activation="relu"))
 #Adding Output Layer
ann.add(tf.keras.layers.Dense(units=1,activation="sigmoid"))
#Compiling ANN
ann.compile(optimizer="adam",loss="binary_crossentropy",metrics=['accuracy'])
#Fitting ANN
ann.fit(X_train,Y_train,batch_size=32,epochs = 10)
#Predicting result for Single Observation
y_pred=ann.predict(X_test)
##
import itertools
y_pred = list(itertools.chain(*y_pred))