
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import Lasso
from sklearn.linear_model import Ridge
from sklearn.linear_model import RidgeCV
from sklearn.model_selection import RepeatedKFold
from numpy import arange
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
from sklearn.neighbors import KNeighborsRegressor
from sklearn.svm import SVR
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import BayesianRidge
from sklearn.ensemble import RandomForestRegressor
from lightgbm import LGBMRegressor


pd.set_option('display.width', 1200)
pd.set_option('display.max_columns', 25)


taxi = pd.read_csv('M1_final.csv')
taxi.head()


col_names = {"OP_UNIQUE_CARRIER":"CARRIER_CODE",
                "TAIL_NUM":"FLIGHT_NO",
                "CRS_ELAPSED_TIME":"SCHEDULED_DURATION",
                "CRS_DEP_M":"SCHEDULED_DEPARTURE",
                "DEP_TIME_M":"ACTUAL_DEP_TIME",
                "CRS_ARR_M":"SCHEDULED_ARRIVAL",
                "sch_dep":"FLT_SCH_ARRIVAL",
                "sch_arr":"FLT_SCH_DEPARTURE"}

taxi = taxi.rename(col_names, axis=1)
taxi.head()


taxi.isnull().sum() # will show the total number of missing values for each feature

MONTH                  0
DAY_OF_MONTH           0
DAY_OF_WEEK            0
CARRIER_CODE           0
FLIGHT_NO              0
DEST                   0
DEP_DELAY              0
SCHEDULED_DURATION     0
DISTANCE               0
SCHEDULED_DEPARTURE    0
ACTUAL_DEP_TIME        0
SCHEDULED_ARRIVAL      0
Temperature            0
Dew Point              0
Humidity               0
Wind                   2
Wind Speed             0
Wind Gust              0
Pressure               0
Condition              0
FLT_SCH_ARRIVAL        0
FLT_SCH_DEPARTURE      0
TAXI_OUT               0
dtype: int64


taxi = taxi.dropna() # drop rows with missing values, reassign the dataframe with no null values as taxi
taxi.isnull().sum() # check to see the missing values have been dropped

MONTH                  0
DAY_OF_MONTH           0
DAY_OF_WEEK            0
CARRIER_CODE           0
FLIGHT_NO              0
DEST                   0
DEP_DELAY              0
SCHEDULED_DURATION     0
DISTANCE               0
SCHEDULED_DEPARTURE    0
ACTUAL_DEP_TIME        0
SCHEDULED_ARRIVAL      0
Temperature            0
Dew Point              0
Humidity               0
Wind                   0
Wind Speed             0
Wind Gust              0
Pressure               0
Condition              0
FLT_SCH_ARRIVAL        0
FLT_SCH_DEPARTURE      0
TAXI_OUT               0
dtype: int64


pd.set_option('display.max_columns', 120) # configure dataframe to show all columns

dest = taxi.drop(columns=['MONTH', 'DAY_OF_MONTH', 'DAY_OF_WEEK']) # create new dataframe from taxi and drop the date columns

dest.groupby(['DEST']).describe() # creates dataframe grouped by destinations, showing details on relevant columns' numerical data.


taxi.groupby(['DEST']).count() # show the counts of each feature for each destination


pd.set_option('display.max_columns', 120) # configure dataframe to show all columns

condition = taxi.drop(columns=['MONTH', 'DAY_OF_MONTH', 'DAY_OF_WEEK']) # create new dataframe from taxi and drop the date columns

condition.groupby(['Condition']).describe() # creates dataframe grouped by Conditions, showing details on relevant columns' numerical data.


# Sorting values by date
taxi.sort_values(by=['MONTH', 'DAY_OF_WEEK', 'DAY_OF_MONTH'])


# Sorting values by carrier code
taxi.sort_values(by='CARRIER_CODE')


taxiCV = taxi.drop(columns=['MONTH', 'DAY_OF_MONTH', 'DAY_OF_WEEK', 'CARRIER_CODE', 'FLIGHT_NO', 'DEST', 'Wind', 'Condition'])
taxiCV


X = taxiCV.iloc[:-1, 0:14] # set predicting variables (initially trying all of them except taxi out time, k = n) from taxiCV
y = taxiCV.iloc[:-1, 14] # set variable of what we want to predict (taxi out time)

# Define model evaluation method with 15 fold cross-validation
cv = RepeatedKFold(n_splits=15, n_repeats=3, random_state=1) 

# Defining the model with 3 alphas of 0, 1, and 0.01 (λ), one for each n_repeat
taxi_model = RidgeCV(alphas=arange(0, 1, 0.01), cv=cv, scoring='neg_mean_absolute_error') 

# Fitting the model
taxi_model.fit(X, y) 

# Summarise chosen configuration
print('alpha: %f' % taxi_model.alpha_) # λ = 0.99

alpha: 0.990000


# Using X and y from k-Fold CV above, split dataset with ratio of train to test of 90:10
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=1) # test_size set to 0.1 because we want 0.9 train_size, random_state can be any integer


X_train # Show X_train


y_train # Show y_train

12992    26
27682    18
16171    21
15508    12
4622     26
         ..
10955    35
17291     9
5192     25
12172    14
235      23
Name: TAXI_OUT, Length: 25935, dtype: int64


X_test # Show X_test


y_test # Show y_test

1637     20
22484    33
14604    31
5945     19
26858    16
         ..
4184     14
938      10
25913    15
5549     21
8351     27
Name: TAXI_OUT, Length: 2882, dtype: int64


print(X_train.shape,X_test.shape,y_train.shape,y_test.shape) # Show sizes of train and test data

(25935, 14) (2882, 14) (25935,) (2882,)


# Create a linear regression object called lreg
lreg = LinearRegression()  

# Perform the linear regression using X_train and y_train
lreg.fit(X_train, y_train)  

# Make predictions based on the model
y_pred = lreg.predict(X_test)  


# Calculate the mean squared error, **0.5 will square root the mean squared error
rmse = mean_squared_error(y_test,y_pred)**0.5
print(rmse) # rmse = 6.575824000116706

6.575824000116706


# define model
ridge_mod = Ridge(alpha=0.05)

# fit model
ridge_mod.fit(X_train, y_train)

# make prediction
ridge_pred = ridge_mod.predict(X_test)

# Calculate the mean squared error
rmser = mean_squared_error(y_test,ridge_pred)**0.5
print(rmser) #rmser = 6.5758241217961 when alpha is 0.05)

6.5758241217961


# define model
lasso_mod = Lasso(alpha=0.05)

# fit model
lasso_mod.fit(X_train, y_train)

# make prediction
lasso_pred = lasso_mod.predict(X_test)

# Calculate the mean squared error
rmsel = mean_squared_error(y_test,lasso_pred)**0.5
print(rmsel) #rmsel = 6.5813630250458015 when alpha is 0.05)

6.5813630250458015


# define model
knnr = KNeighborsRegressor(n_neighbors=200)

# fit model
knnr.fit(X_train,y_train)

# make prediction
knn_pred = knnr.predict(X_test)

# Calculate the mean squared error
rmsek = mean_squared_error(y_test,knn_pred)**0.5
print(rmsek) #rmsek = 6.665877509387613 when n_neighbours is 200)

6.665877509387613


# define model
sc1 = StandardScaler()
sc2 = StandardScaler()

x1 = X_train.copy()
x2 = X_test.copy()

# fit model 
x1 = sc1.fit_transform(x1)
x2 = sc2.fit_transform(x2)
svr=SVR()
svr.fit(x1,y_train)

# make prediction
svr_pred = svr.predict(x2)

# Calculate the mean squared error
rmsesv = mean_squared_error(y_test,svr_pred)**0.5
print(rmsesv) #rmsesv = 6.4861562011648095

6.4861562011648095


# define model
bay_mod = BayesianRidge()

# fit model
bay_mod.fit(X_train,y_train)

# make prediction
bay_pred = bay_mod.predict(X_test)

# Calculate the mean squared error
rmseb = mean_squared_error(y_test,bay_pred)**0.5
print(rmseb) #rmseb = 6.57981846296084

6.57981846296084


# define model
rf_mod = RandomForestRegressor()

# fit model
rf_mod.fit(X_train,y_train)

#make prediction
rf_pred = rf_mod.predict(X_test)

# Calculate the mean squared error
rmserf = mean_squared_error(y_test,rf_pred)**0.5
print(rmserf) #rmserf = 5.664840253147916

5.664840253147916


# lgbm = LGBMRegressor()

# lgbm.fit(X_train,y_train)

# lgbm_pred = lgbm.predict(X_test)

# # Calculate the mean squared error
# rmselgbm = mean_squared_error(y_test,lgbm_pred)**0.5
# print(rmselgbm) #rmselgbm = ?

	DEP_DELAY								SCHEDULED_DURATION								DISTANCE								SCHEDULED_DEPARTURE								ACTUAL_DEP_TIME								SCHEDULED_ARRIVAL								Temperature								Humidity								Wind Speed								Wind Gust								Pressure								FLT_SCH_ARRIVAL								FLT_SCH_DEPARTURE								TAXI_OUT
	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max
DEST
ABQ	58.0	10.327586	39.259098	-13.0	-6.75	-3.0	7.00	215.0	58.0	310.258621	3.522162	307.0	307.0	307.0	314.0	314.0	58.0	1826.0	0.0	1826.0	1826.0	1826.0	1826.0	1826.0	58.0	1195.844828	4.697150	1189.0	1193.0	1200.0	1200.0	1200.0	58.0	1206.172414	40.006200	1178.0	1190.00	1194.0	1203.25	1415.0	58.0	1386.103448	1.682622	1383.0	1387.0	1387.0	1387.0	1387.0	58.0	41.758621	7.472312	26.0	36.00	42.0	48.0	56.0	58.0	62.327586	23.869814	10.0	49.25	61.0	84.25	97.0	58.0	11.948276	5.325946	0.0	7.25	12.0	16.00	25.0	58.0	5.551724	11.050399	0.0	0.0	0.0	0.0	33.0	58.0	30.083966	0.305424	29.38	29.8925	30.095	30.2975	30.73	58.0	37.189655	6.974784	19.0	33.0	40.0	41.75	47.0	58.0	31.465517	5.737582	13.0	28.0	31.0	33.75	43.0	58.0	22.620690	8.243717	11.0	15.0	21.0	29.0	41.0
ATL	795.0	6.725786	26.290094	-13.0	-4.00	-1.0	6.50	341.0	795.0	158.148428	6.547875	136.0	155.0	158.0	163.0	172.0	795.0	760.0	0.0	760.0	760.0	760.0	760.0	760.0	795.0	780.316981	280.985778	315.0	510.0	833.0	1015.0	1275.0	795.0	787.042767	285.398459	314.0	509.00	835.0	1012.00	1356.0	795.0	938.465409	284.157564	463.0	665.0	983.0	1169.0	1433.0	795.0	41.530818	8.252013	17.0	35.50	42.0	47.0	67.0	795.0	57.201258	23.670753	10.0	45.00	59.0	74.00	97.0	795.0	12.396226	6.267162	0.0	8.00	12.0	16.00	36.0	795.0	5.322013	11.705322	0.0	0.0	0.0	0.0	47.0	795.0	30.086679	0.294683	29.21	29.8800	30.110	30.3100	30.74	795.0	30.070440	10.505849	6.0	26.0	30.0	36.00	55.0	795.0	28.817610	8.360167	13.0	20.0	31.0	36.00	45.0	795.0	19.272956	6.881488	7.0	14.0	18.0	23.0	41.0
AUS	485.0	4.682474	27.899950	-14.0	-6.00	-3.0	1.00	219.0	485.0	261.525773	6.883765	237.0	257.0	263.0	265.0	277.0	485.0	1521.0	0.0	1521.0	1521.0	1521.0	1521.0	1521.0	485.0	915.839175	327.606022	432.0	555.0	1090.0	1259.0	1391.0	485.0	905.676289	340.460645	4.0	551.00	826.0	1259.00	1432.0	485.0	710.602062	473.716208	29.0	68.0	752.0	1020.0	1439.0	485.0	41.059794	7.876535	21.0	35.00	41.0	47.0	67.0	485.0	58.736082	23.388394	10.0	47.00	60.0	75.00	97.0	485.0	12.484536	6.251799	0.0	8.00	12.0	16.00	35.0	485.0	5.171134	11.672068	0.0	0.0	0.0	0.0	45.0	485.0	30.102474	0.296995	29.23	29.8800	30.120	30.3300	30.74	485.0	34.263918	8.710237	3.0	29.0	33.0	39.00	55.0	485.0	28.070103	8.684985	3.0	20.0	30.0	35.00	45.0	485.0	19.226804	6.192346	9.0	15.0	18.0	23.0	41.0
BNA	366.0	4.106557	30.840324	-14.0	-8.00	-4.5	0.00	199.0	366.0	166.013661	5.357604	154.0	163.0	165.0	170.0	175.0	366.0	765.0	0.0	765.0	765.0	765.0	765.0	765.0	366.0	919.994536	247.202429	485.0	815.0	951.0	1135.0	1230.0	366.0	924.101093	248.513042	483.0	810.00	945.5	1131.00	1302.0	366.0	1026.008197	245.996085	580.0	919.0	1066.0	1241.0	1337.0	366.0	42.232240	7.778308	23.0	36.00	42.0	48.0	67.0	366.0	57.677596	22.930984	10.0	45.25	58.5	73.00	97.0	366.0	12.543716	6.352392	0.0	8.00	12.0	16.00	35.0	366.0	6.109290	12.318115	0.0	0.0	0.0	0.0	45.0	366.0	30.093907	0.291997	29.23	29.8900	30.110	30.3100	30.74	366.0	36.155738	7.914634	20.0	29.0	37.0	41.00	55.0	366.0	32.191257	8.488286	12.0	28.0	34.5	38.00	45.0	366.0	19.702186	7.110967	7.0	15.0	19.0	24.0	41.0
BOS	1243.0	10.536605	43.788570	-16.0	-6.00	-3.0	3.50	515.0	1243.0	78.744167	7.367545	66.0	73.0	79.0	83.0	104.0	1243.0	187.0	0.0	187.0	187.0	187.0	187.0	187.0	1243.0	870.674980	315.771158	360.0	597.0	862.0	1165.0	1395.0	1243.0	861.517297	326.669282	2.0	569.00	849.0	1137.50	1436.0	1243.0	821.985519	371.751796	3.0	555.0	833.0	1108.0	1430.0	1243.0	41.448109	8.122324	18.0	36.00	42.0	47.0	67.0	1243.0	57.622687	23.067360	10.0	46.00	58.0	73.50	97.0	1243.0	12.336283	6.314327	0.0	8.00	12.0	16.00	35.0	1243.0	5.577635	11.979090	0.0	0.0	0.0	0.0	49.0	1243.0	30.102904	0.292522	29.22	29.8900	30.120	30.3300	30.75	1243.0	28.242156	8.278958	1.0	21.0	29.0	34.00	52.0	1243.0	27.872084	7.799142	0.0	21.0	29.0	34.00	46.0	1243.0	20.218825	6.371894	9.0	16.0	19.0	24.0	41.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
SMF	82.0	11.292683	30.616903	-10.0	-5.00	-1.0	12.25	151.0	82.0	385.951220	7.525926	379.0	379.0	379.0	394.0	394.0	82.0	2521.0	0.0	2521.0	2521.0	2521.0	2521.0	2521.0	82.0	1026.963415	20.042206	1000.0	1019.0	1020.0	1052.0	1052.0	82.0	1038.256098	36.266779	992.0	1015.00	1037.0	1054.00	1171.0	82.0	1232.914634	15.285918	1214.0	1218.0	1234.0	1251.0	1251.0	82.0	41.768293	7.204763	25.0	37.00	41.5	46.0	61.0	82.0	55.878049	22.971475	10.0	44.25	57.0	70.00	96.0	82.0	12.182927	5.604513	0.0	7.25	12.0	16.75	25.0	82.0	4.195122	10.282958	0.0	0.0	0.0	0.0	35.0	82.0	30.083171	0.292751	29.22	29.9000	30.110	30.3000	30.74	82.0	30.219512	4.000075	20.0	28.0	30.0	32.00	42.0	82.0	30.646341	2.786085	24.0	28.0	31.0	32.00	38.0	82.0	18.878049	5.774337	11.0	15.0	18.0	22.0	38.0
SRQ	105.0	4.942857	39.103617	-13.0	-6.00	-3.0	2.00	372.0	105.0	189.952381	7.836528	183.0	184.0	190.0	190.0	209.0	105.0	1041.0	0.0	1041.0	1041.0	1041.0	1041.0	1041.0	105.0	535.780952	58.645936	449.0	490.0	560.0	568.0	614.0	105.0	540.723810	71.747219	440.0	486.00	561.0	582.00	932.0	105.0	725.733333	56.251370	633.0	692.0	744.0	752.0	804.0	105.0	40.714286	8.015267	21.0	37.00	40.0	46.0	60.0	105.0	58.914286	24.412762	10.0	48.00	61.0	77.00	97.0	105.0	12.228571	6.498901	0.0	7.00	10.0	16.00	31.0	105.0	5.447619	11.931681	0.0	0.0	0.0	0.0	41.0	105.0	30.096571	0.307286	29.23	29.8300	30.130	30.3300	30.73	105.0	35.885714	9.020611	17.0	31.0	36.0	41.00	55.0	105.0	22.866667	7.037081	11.0	19.0	20.0	23.00	37.0	105.0	19.895238	6.139287	10.0	15.0	19.0	24.0	38.0
STT	62.0	0.467742	11.465869	-10.0	-5.75	-3.0	0.00	43.0	62.0	234.451613	3.700587	228.0	232.0	232.5	238.0	243.0	62.0	1623.0	0.0	1623.0	1623.0	1623.0	1623.0	1623.0	62.0	516.838710	39.070006	492.0	492.0	515.0	515.0	680.0	62.0	517.306452	42.409243	485.0	501.25	510.0	514.00	723.0	62.0	809.354839	40.533369	746.0	790.0	807.0	807.0	975.0	62.0	39.403226	8.237180	22.0	34.25	39.5	45.0	61.0	62.0	55.629032	25.873104	10.0	48.00	60.0	71.50	97.0	62.0	12.693548	6.674121	0.0	8.25	12.0	16.75	31.0	62.0	7.241935	13.233942	0.0	0.0	0.0	0.0	41.0	62.0	30.126613	0.323571	29.26	29.8700	30.190	30.3475	30.73	62.0	47.483871	5.833037	20.0	45.0	47.5	51.00	55.0	62.0	17.919355	1.884348	12.0	17.0	18.0	19.00	23.0	62.0	26.661290	7.539934	14.0	21.0	27.0	33.5	40.0
SYR	389.0	5.511568	33.195267	-15.0	-7.00	-5.0	-1.00	262.0	389.0	82.293059	7.185788	69.0	76.0	80.0	90.0	98.0	389.0	209.0	0.0	209.0	209.0	209.0	209.0	209.0	389.0	853.347044	308.978823	395.0	605.0	989.0	1139.0	1327.0	389.0	858.858612	312.447328	408.0	600.00	997.0	1134.00	1366.0	389.0	935.640103	311.894079	464.0	697.0	1082.0	1215.0	1410.0	389.0	41.282776	7.971744	18.0	36.00	42.0	47.0	65.0	389.0	58.683805	23.231916	10.0	48.00	59.0	75.00	97.0	389.0	12.244216	6.089072	0.0	8.00	12.0	16.00	31.0	389.0	4.773779	11.230262	0.0	0.0	0.0	0.0	49.0	389.0	30.091465	0.290771	29.22	29.8800	30.110	30.3100	30.74	389.0	29.935733	8.991031	12.0	21.0	30.0	38.00	54.0	389.0	28.357326	6.647093	14.0	22.0	30.0	34.00	45.0	389.0	20.935733	6.678052	9.0	16.0	20.0	25.0	41.0
TPA	664.0	4.840361	34.281751	-12.0	-6.00	-3.0	1.00	585.0	664.0	183.298193	5.470469	165.0	179.0	183.0	187.0	194.0	664.0	1005.0	0.0	1005.0	1005.0	1005.0	1005.0	1005.0	664.0	839.063253	290.194015	390.0	490.0	885.0	1079.0	1325.0	664.0	841.734940	294.483476	140.0	495.50	882.0	1092.50	1439.0	664.0	851.036145	378.232276	35.0	651.0	882.0	1130.0	1360.0	664.0	41.605422	7.947852	18.0	36.00	42.0	47.0	65.0	664.0	56.519578	23.818055	10.0	45.00	58.0	73.00	97.0	664.0	12.469880	6.102864	0.0	8.00	12.0	17.00	31.0	664.0	5.554217	11.731926	0.0	0.0	0.0	0.0	44.0	664.0	30.089744	0.298325	29.21	29.8700	30.120	30.3100	30.74	664.0	32.932229	7.714744	3.0	28.0	31.0	38.00	55.0	664.0	29.646084	7.312032	4.0	23.0	31.0	35.00	45.0	664.0	19.992470	6.836262	8.0	15.0	19.0	24.0	41.0

	MONTH	DAY_OF_MONTH	DAY_OF_WEEK	CARRIER_CODE	FLIGHT_NO	DEP_DELAY	SCHEDULED_DURATION	DISTANCE	SCHEDULED_DEPARTURE	ACTUAL_DEP_TIME	SCHEDULED_ARRIVAL	Temperature	Dew Point	Humidity	Wind	Wind Speed	Wind Gust	Pressure	Condition	FLT_SCH_ARRIVAL	FLT_SCH_DEPARTURE	TAXI_OUT
DEST
ABQ	58	58	58	58	58	58	58	58	58	58	58	58	58	58	58	58	58	58	58	58	58	58
ATL	795	795	795	795	795	795	795	795	795	795	795	795	795	795	795	795	795	795	795	795	795	795
AUS	485	485	485	485	485	485	485	485	485	485	485	485	485	485	485	485	485	485	485	485	485	485
BNA	366	366	366	366	366	366	366	366	366	366	366	366	366	366	366	366	366	366	366	366	366	366
BOS	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243	1243
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
SMF	82	82	82	82	82	82	82	82	82	82	82	82	82	82	82	82	82	82	82	82	82	82
SRQ	105	105	105	105	105	105	105	105	105	105	105	105	105	105	105	105	105	105	105	105	105	105
STT	62	62	62	62	62	62	62	62	62	62	62	62	62	62	62	62	62	62	62	62	62	62
SYR	389	389	389	389	389	389	389	389	389	389	389	389	389	389	389	389	389	389	389	389	389	389
TPA	664	664	664	664	664	664	664	664	664	664	664	664	664	664	664	664	664	664	664	664	664	664

	DEP_DELAY								SCHEDULED_DURATION								DISTANCE								SCHEDULED_DEPARTURE								ACTUAL_DEP_TIME								SCHEDULED_ARRIVAL								Temperature								Humidity								Wind Speed								Wind Gust								Pressure								FLT_SCH_ARRIVAL								FLT_SCH_DEPARTURE								TAXI_OUT
	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max	count	mean	std	min	25%	50%	75%	max
Condition
Cloudy	4992.0	5.316106	38.055821	-22.0	-6.00	-3.0	0.00	1048.0	4992.0	225.112380	117.825273	57.0	125.00	189.5	365.00	697.0	4992.0	1264.958934	875.580354	94.0	483.00	1041.0	2248.00	4983.0	4992.0	825.221554	304.417077	301.0	531.75	857.0	1095.00	1439.0	4992.0	818.999199	311.664436	2.0	523.00	848.0	1092.00	1440.0	4992.0	909.312300	345.897879	1.0	662.00	917.0	1194.00	1439.0	4992.0	43.303486	7.217202	21.0	39.00	43.0	48.0	61.0	4992.0	63.158654	27.643813	10.0	52.00	70.0	85.25	97.0	4992.0	9.875401	4.390900	0.0	7.00	9.0	13.00	20.0	4992.0	0.990184	4.848259	0.0	0.0	0.0	0.0	30.0	4992.0	30.036973	3.143069e-01	29.22	29.810	30.020	30.2825	30.74	4992.0	30.476362	9.926571	0.0	25.00	30.0	37.00	54.0	4992.0	28.195913	8.576998	0.0	20.00	29.0	35.0	45.0	4992.0	20.258814	6.362420	7.0	16.00	19.0	24.00	41.0
Cloudy / Windy	341.0	18.695015	54.967806	-15.0	-6.00	-3.0	10.00	372.0	341.0	215.105572	110.922525	57.0	125.00	183.0	334.00	424.0	341.0	1191.331378	821.225672	94.0	483.00	1005.0	1990.00	2586.0	341.0	1006.175953	262.500451	301.0	840.00	1089.0	1214.00	1439.0	341.0	995.310850	303.706103	43.0	824.00	1084.0	1231.00	1433.0	341.0	1003.803519	412.285780	1.0	876.00	1076.0	1339.00	1439.0	341.0	42.560117	5.188794	34.0	40.00	41.0	44.0	57.0	341.0	70.114370	15.997844	10.0	65.00	67.0	77.00	97.0	341.0	23.143695	2.774866	21.0	22.00	22.0	23.00	31.0	341.0	23.398827	13.667454	0.0	28.0	30.0	31.0	44.0	341.0	29.871408	3.133309e-01	29.29	29.610	29.890	30.1200	30.27	341.0	27.445748	7.211153	0.0	24.00	29.0	30.00	41.0	341.0	30.011730	7.867273	3.0	24.00	31.0	35.0	44.0	341.0	20.970674	7.001619	7.0	16.00	20.0	25.00	41.0
Drizzle and Fog	5.0	-3.000000	5.700877	-7.0	-6.00	-5.0	-4.00	7.0	5.0	283.400000	149.106673	93.0	151.00	379.0	387.00	407.0	5.0	1663.400000	1110.715895	213.0	718.00	2378.0	2422.00	2586.0	5.0	570.800000	7.463243	560.0	569.00	570.0	575.00	580.0	5.0	567.800000	3.701351	565.0	565.00	567.0	568.00	574.0	5.0	746.200000	48.100936	673.0	726.00	767.0	768.00	797.0	5.0	46.000000	0.000000	46.0	46.00	46.0	46.0	46.0	5.0	0.000000	0.000000	0.0	0.00	0.0	0.00	0.0	5.0	6.000000	0.000000	6.0	6.00	6.0	6.00	6.0	5.0	0.000000	0.000000	0.0	0.0	0.0	0.0	0.0	5.0	29.660000	3.972055e-15	29.66	29.660	29.660	29.6600	29.66	5.0	40.000000	0.000000	40.0	40.00	40.0	40.00	40.0	5.0	13.000000	0.000000	13.0	13.00	13.0	13.0	13.0	5.0	32.600000	5.128353	27.0	29.00	32.0	35.00	40.0
Fair	5038.0	6.032553	37.086923	-18.0	-6.00	-3.0	1.00	830.0	5038.0	227.434895	119.711126	57.0	125.00	190.0	367.00	697.0	5038.0	1283.190155	889.593552	94.0	483.00	1069.0	2248.00	4983.0	5038.0	834.307265	319.986273	301.0	510.00	860.0	1130.00	1439.0	5038.0	832.908297	325.661777	3.0	508.00	859.5	1135.75	1440.0	5038.0	894.080389	371.688500	1.0	632.00	894.0	1225.00	1439.0	5038.0	38.084756	8.861102	19.0	32.00	36.0	44.0	61.0	5038.0	54.123660	15.445074	10.0	44.00	52.0	66.00	97.0	5038.0	11.679436	4.427325	0.0	8.00	12.0	15.00	20.0	5038.0	3.669909	9.032380	0.0	0.0	0.0	0.0	37.0	5038.0	30.262622	2.247688e-01	29.55	30.110	30.280	30.4200	30.75	5038.0	30.778881	10.108010	0.0	25.00	30.5	38.00	55.0	5038.0	28.127233	8.104287	0.0	21.00	30.0	35.0	45.0	5038.0	20.240969	6.507207	6.0	15.00	19.0	24.00	41.0
Fair / Windy	918.0	9.896514	55.643271	-15.0	-5.00	-2.0	4.00	1276.0	918.0	224.440087	117.682002	59.0	127.25	188.0	357.75	675.0	918.0	1276.844227	878.432511	94.0	509.00	1069.0	2248.00	4983.0	918.0	704.971678	312.077716	301.0	479.00	560.0	1040.00	1439.0	918.0	703.887800	317.589702	17.0	475.00	555.5	1075.25	1435.0	918.0	813.333333	324.579349	3.0	617.00	701.5	1043.75	1439.0	918.0	33.820261	11.286946	17.0	25.00	32.0	40.0	64.0	918.0	48.150327	10.353788	24.0	43.00	48.0	54.00	68.0	918.0	23.289760	2.461242	21.0	22.00	23.0	24.00	36.0	918.0	29.519608	9.830468	0.0	30.0	32.0	33.0	46.0	918.0	30.232887	2.494650e-01	29.50	30.090	30.260	30.3600	30.63	918.0	32.397603	11.963497	0.0	21.00	33.0	40.00	53.0	918.0	25.255991	8.099359	3.0	19.00	23.0	34.0	45.0	918.0	21.265795	7.242576	8.0	16.00	20.0	25.00	41.0
Fog	147.0	2.639456	19.265252	-13.0	-5.00	-3.0	2.50	132.0	147.0	208.448980	114.798703	71.0	112.00	182.0	337.00	412.0	147.0	1161.319728	848.563742	184.0	425.00	1005.0	1990.00	2586.0	147.0	618.448980	150.457621	389.0	450.00	677.0	710.00	1309.0	147.0	611.292517	151.109106	1.0	446.50	680.0	708.00	843.0	147.0	768.938776	156.354761	91.0	631.00	823.0	879.00	1035.0	147.0	48.659864	7.382408	33.0	46.00	52.0	55.0	55.0	147.0	10.000000	0.000000	10.0	10.00	10.0	10.00	10.0	147.0	10.632653	5.070843	3.0	6.00	8.0	16.00	20.0	147.0	0.000000	0.000000	0.0	0.0	0.0	0.0	0.0	147.0	29.760340	3.563983e-01	29.22	29.330	29.870	30.0100	30.28	147.0	27.972789	7.792643	13.0	21.00	26.0	32.00	44.0	147.0	25.965986	8.066008	10.0	21.00	21.0	34.0	42.0	147.0	24.965986	7.626930	10.0	18.00	25.0	30.00	41.0
Fog / Windy	28.0	25.892857	74.707003	-11.0	-2.25	0.5	28.50	390.0	28.0	207.964286	109.032609	83.0	124.75	170.0	302.00	404.0	28.0	1135.714286	830.919475	213.0	405.25	894.0	1717.00	2586.0	28.0	825.357143	182.387909	360.0	867.50	895.5	899.00	952.0	28.0	851.250000	176.075452	349.0	890.25	897.5	932.00	953.0	28.0	986.178571	180.062963	517.0	994.75	1032.0	1072.25	1164.0	28.0	52.535714	1.261455	52.0	52.00	52.0	52.0	56.0	28.0	10.000000	0.000000	10.0	10.00	10.0	10.00	10.0	28.0	23.500000	4.434712	21.0	22.00	22.0	22.00	36.0	28.0	4.928571	14.488638	0.0	0.0	0.0	0.0	46.0	28.0	29.276071	2.060446e-01	29.20	29.200	29.210	29.2100	29.86	28.0	24.464286	5.460173	7.0	24.00	24.0	28.00	28.0	28.0	35.892857	5.573345	21.0	35.00	35.0	40.0	40.0	28.0	16.928571	3.799889	10.0	14.75	16.5	18.50	25.0
Heavy Rain	54.0	35.611111	71.089743	-9.0	-2.00	9.0	27.25	325.0	54.0	228.518519	106.586618	81.0	145.00	206.0	314.25	417.0	54.0	1280.740741	790.174454	184.0	608.00	1051.5	1892.00	2586.0	54.0	909.962963	291.175689	420.0	779.25	1016.5	1139.00	1412.0	54.0	918.907407	311.962157	155.0	565.25	1017.0	1167.00	1216.0	54.0	1060.703704	321.161902	258.0	740.75	1203.5	1310.00	1439.0	54.0	49.518519	3.446304	37.0	48.00	51.0	52.0	55.0	54.0	10.000000	0.000000	10.0	10.00	10.0	10.00	10.0	54.0	12.148148	4.923595	3.0	12.00	14.0	16.00	17.0	54.0	1.907407	6.808065	0.0	0.0	0.0	0.0	26.0	54.0	29.852037	1.737204e-01	29.29	29.790	29.820	29.8800	30.12	54.0	34.981481	7.053678	2.0	31.00	37.0	37.00	42.0	54.0	32.648148	5.600396	2.0	29.50	32.5	36.0	42.0	54.0	27.037037	8.032864	12.0	21.00	26.0	34.50	41.0
Heavy Rain / Windy	6.0	1.166667	24.701552	-19.0	-9.75	-6.5	-1.75	50.0	6.0	222.666667	132.382275	81.0	143.00	171.0	334.75	390.0	6.0	1257.000000	978.368847	184.0	684.00	886.0	2092.25	2475.0	6.0	863.666667	24.848877	819.0	862.25	869.0	869.75	895.0	6.0	864.833333	8.908797	850.0	861.50	867.0	868.75	876.0	6.0	1026.333333	49.854455	956.0	989.50	1040.0	1065.00	1076.0	6.0	47.000000	0.000000	47.0	47.00	47.0	47.0	47.0	6.0	10.000000	0.000000	10.0	10.00	10.0	10.00	10.0	6.0	25.000000	0.000000	25.0	25.00	25.0	25.00	25.0	6.0	32.000000	0.000000	32.0	32.0	32.0	32.0	32.0	6.0	29.750000	0.000000e+00	29.75	29.750	29.750	29.7500	29.75	6.0	22.000000	0.000000	22.0	22.00	22.0	22.00	22.0	6.0	40.000000	0.000000	40.0	40.00	40.0	40.0	40.0	6.0	15.833333	3.430258	12.0	14.25	15.0	16.50	22.0
Light Drizzle	194.0	3.958763	30.807918	-16.0	-6.00	-3.0	0.00	228.0	194.0	234.262887	134.940240	57.0	121.00	191.0	366.50	697.0	194.0	1338.381443	1009.767925	150.0	427.00	1055.0	2248.00	4983.0	194.0	683.649485	263.334459	301.0	486.25	629.0	762.25	1439.0	194.0	687.608247	269.968931	296.0	500.25	624.0	757.50	1430.0	194.0	750.283505	262.159934	2.0	642.00	785.5	892.00	1439.0	194.0	44.886598	3.068733	38.0	44.00	46.0	47.0	49.0	194.0	22.639175	29.649484	10.0	10.00	10.0	10.00	97.0	194.0	7.716495	3.363479	0.0	6.00	7.0	10.00	14.0	194.0	0.000000	0.000000	0.0	0.0	0.0	0.0	0.0	194.0	29.874433	2.677036e-01	29.54	29.670	29.835	30.1300	30.36	194.0	29.180412	10.507507	1.0	19.00	32.0	38.00	50.0	194.0	23.221649	7.179948	4.0	17.00	23.0	29.0	35.0	194.0	21.659794	6.907811	10.0	16.00	21.0	26.00	41.0
Light Drizzle / Windy	18.0	-0.722222	12.512608	-10.0	-6.00	-2.5	-1.00	47.0	18.0	248.166667	96.359163	116.0	185.25	196.5	321.75	412.0	18.0	1436.444444	690.955879	427.0	1010.75	1079.0	1929.00	2586.0	18.0	699.500000	104.018805	616.0	667.50	685.0	688.75	1109.0	18.0	698.777778	103.757384	652.0	666.25	678.5	683.75	1112.0	18.0	891.000000	114.517915	798.0	851.00	874.5	883.25	1313.0	18.0	42.888889	0.471405	41.0	43.00	43.0	43.0	43.0	18.0	96.944444	0.235702	96.0	97.00	97.0	97.00	97.0	18.0	22.000000	0.000000	22.0	22.00	22.0	22.00	22.0	18.0	29.277778	7.306770	0.0	31.0	31.0	31.0	31.0	18.0	29.759444	2.357023e-03	29.75	29.760	29.760	29.7600	29.76	18.0	29.833333	2.407097	25.0	30.00	30.0	30.00	37.0	18.0	21.277778	4.041048	20.0	20.00	20.0	20.0	37.0	18.0	29.111111	7.291324	15.0	27.00	31.0	33.75	40.0
Light Freezing Rain	4.0	70.000000	140.748002	-7.0	-0.25	3.0	73.25	281.0	4.0	215.250000	121.817828	88.0	149.50	198.0	263.75	377.0	4.0	1326.250000	934.086497	288.0	780.00	1271.0	1817.25	2475.0	4.0	870.250000	361.190047	685.0	688.00	692.0	874.25	1412.0	4.0	580.250000	218.182454	253.0	578.50	687.5	689.25	693.0	4.0	695.500000	294.840635	258.0	651.75	819.0	862.75	886.0	4.0	32.750000	0.500000	32.0	32.75	33.0	33.0	33.0	4.0	58.750000	32.500000	10.0	58.75	75.0	75.00	75.0	4.0	12.250000	1.500000	10.0	12.25	13.0	13.00	13.0	4.0	0.000000	0.000000	0.0	0.0	0.0	0.0	0.0	4.0	29.917500	7.500000e-02	29.88	29.880	29.880	29.9175	30.03	4.0	24.250000	15.500000	1.0	24.25	32.0	32.00	32.0	4.0	16.750000	8.500000	4.0	16.75	21.0	21.0	21.0	4.0	30.000000	10.132456	15.0	28.50	34.0	35.50	37.0
Light Rain	1865.0	9.595710	39.942295	-18.0	-5.00	-2.0	7.00	624.0	1865.0	227.034316	120.382157	57.0	122.00	189.0	366.00	697.0	1865.0	1280.980161	897.352892	94.0	427.00	1041.0	2248.00	4983.0	1865.0	876.163539	314.208821	301.0	562.00	929.0	1165.00	1439.0	1865.0	881.126542	319.224426	3.0	565.00	940.0	1164.00	1440.0	1865.0	925.996783	380.345040	1.0	659.00	995.0	1257.00	1439.0	1865.0	43.217694	5.974805	33.0	39.00	42.0	48.0	57.0	1865.0	40.334584	37.709239	10.0	10.00	10.0	86.00	97.0	1865.0	11.438070	4.954790	0.0	8.00	12.0	15.00	20.0	1865.0	3.079893	8.456690	0.0	0.0	0.0	0.0	33.0	1865.0	29.815845	2.164966e-01	29.21	29.700	29.810	29.9600	30.27	1865.0	31.615550	9.255011	0.0	27.00	31.0	37.00	54.0	1865.0	29.500804	7.873335	3.0	22.00	31.0	35.0	46.0	1865.0	22.221448	7.526047	7.0	16.00	21.0	27.00	41.0
Light Rain / Windy	288.0	6.236111	28.498178	-18.0	-6.00	-3.0	3.00	195.0	288.0	205.538194	116.500745	59.0	109.25	174.5	301.75	685.0	288.0	1140.604167	872.408862	94.0	403.75	886.0	1807.00	4983.0	288.0	816.392361	231.451176	379.0	685.00	806.5	929.00	1439.0	288.0	797.628472	239.793518	1.0	677.75	800.5	918.00	1437.0	288.0	879.430556	275.219827	3.0	786.75	912.5	1039.50	1430.0	288.0	45.138889	5.044901	35.0	42.00	43.0	47.0	68.0	288.0	52.659722	38.211891	10.0	10.00	79.0	86.00	97.0	288.0	24.652778	3.613408	21.0	22.00	24.0	26.00	35.0	288.0	30.722222	11.702732	0.0	29.0	33.0	37.0	47.0	288.0	29.652778	2.576534e-01	29.22	29.400	29.700	29.8500	30.05	288.0	29.232639	9.351333	3.0	25.00	29.0	31.00	52.0	288.0	29.319444	9.710910	3.0	21.50	29.0	38.0	43.0	288.0	24.666667	7.777391	8.0	18.00	24.0	30.00	41.0
Light Snow	76.0	15.144737	56.914838	-14.0	-5.00	-1.5	11.00	421.0	76.0	234.000000	114.427619	75.0	136.25	201.0	370.25	409.0	76.0	1343.065789	843.754488	187.0	636.00	1089.0	2291.50	2586.0	76.0	744.605263	273.215670	301.0	450.00	839.0	942.00	1200.0	76.0	740.802632	287.486163	98.0	448.50	845.5	938.00	1197.0	76.0	917.026316	278.646968	440.0	632.25	971.0	1138.50	1387.0	76.0	32.407895	2.536021	27.0	30.00	34.0	34.0	35.0	76.0	60.960526	32.082577	10.0	10.00	72.0	89.00	92.0	76.0	11.302632	4.647637	5.0	6.00	14.0	15.00	20.0	76.0	1.368421	5.844295	0.0	0.0	0.0	0.0	26.0	76.0	30.067237	2.554818e-01	29.47	29.960	30.190	30.2600	30.39	76.0	30.236842	10.180856	3.0	26.00	30.0	39.00	51.0	76.0	30.078947	7.006213	5.0	24.00	34.0	34.0	45.0	76.0	30.131579	8.959676	11.0	22.75	33.0	38.00	41.0
Light Snow / Windy	24.0	63.625000	79.949882	-10.0	2.25	42.0	110.25	337.0	24.0	163.000000	101.585689	59.0	86.00	127.5	201.00	392.0	24.0	843.333333	758.745284	150.0	266.00	525.0	1077.75	2475.0	24.0	1028.208333	289.023390	677.0	728.75	1068.5	1308.50	1412.0	24.0	911.833333	445.625273	1.0	730.50	750.5	1381.00	1415.0	24.0	863.708333	466.783581	12.0	781.50	889.0	1269.75	1435.0	24.0	31.166667	4.678040	25.0	25.00	31.5	35.0	40.0	24.0	73.666667	15.493804	10.0	69.00	76.0	76.00	96.0	24.0	23.125000	1.918163	21.0	21.00	23.5	25.00	25.0	24.0	30.416667	1.976309	26.0	30.0	30.0	30.0	37.0	24.0	29.871250	1.844218e-01	29.47	29.890	29.890	30.0400	30.04	24.0	20.708333	7.116907	3.0	19.00	21.0	22.25	33.0	24.0	22.541667	8.657639	2.0	20.00	22.5	25.0	41.0	24.0	26.958333	8.824271	12.0	19.75	28.0	33.25	40.0
Mostly Cloudy	9122.0	4.814953	35.935362	-20.0	-6.00	-3.0	0.00	1148.0	9122.0	226.227472	119.924721	57.0	125.00	189.0	367.00	697.0	9122.0	1269.826573	893.186270	94.0	483.00	1029.0	2248.00	4983.0	9122.0	837.198641	293.088139	301.0	550.00	886.0	1080.00	1439.0	9122.0	836.488489	298.025566	1.0	546.00	887.0	1089.00	1440.0	9122.0	923.147665	340.448918	1.0	674.00	975.0	1202.00	1439.0	9122.0	42.028503	7.189348	22.0	37.00	42.0	47.0	65.0	9122.0	63.675729	17.427126	10.0	53.00	63.0	76.00	97.0	9122.0	10.521158	4.846876	0.0	7.00	10.0	14.00	20.0	9122.0	1.505591	6.098434	0.0	0.0	0.0	0.0	35.0	9122.0	30.136221	2.708016e-01	29.21	29.950	30.150	30.3300	30.74	9122.0	31.783162	8.922077	0.0	27.00	31.0	38.00	54.0	9122.0	28.978075	8.146878	0.0	21.00	31.0	36.0	45.0	9122.0	20.469086	6.555405	5.0	16.00	19.0	24.00	41.0
Mostly Cloudy / Windy	1442.0	5.855756	28.663934	-18.0	-6.00	-3.0	2.00	322.0	1442.0	220.796117	119.628926	59.0	123.00	186.0	356.50	685.0	1442.0	1238.634535	890.646853	94.0	441.00	1028.0	2153.00	4983.0	1442.0	748.915395	214.903402	301.0	570.00	720.0	899.00	1439.0	1442.0	752.773925	219.478478	74.0	570.25	728.5	910.00	1439.0	1442.0	886.452150	229.653620	9.0	728.25	880.0	1040.00	1439.0	1442.0	44.452150	7.422101	27.0	39.00	44.0	49.0	67.0	1442.0	58.596394	15.959897	10.0	48.00	55.0	64.00	97.0	1442.0	23.708738	2.848922	21.0	21.00	23.0	25.00	35.0	1442.0	27.993759	13.126591	0.0	28.0	31.0	35.0	49.0	1442.0	29.908322	1.938144e-01	29.23	29.790	29.890	30.0200	30.37	1442.0	30.692788	9.114238	1.0	25.00	30.0	34.00	55.0	1442.0	26.871012	8.907809	2.0	19.00	25.0	36.0	44.0	1442.0	21.651872	6.928866	7.0	16.00	20.0	26.00	41.0
Partly Cloudy	3209.0	5.227174	30.010947	-18.0	-6.00	-3.0	1.00	360.0	3209.0	222.366781	119.638459	57.0	119.00	187.0	363.00	685.0	3209.0	1254.278591	890.523331	94.0	427.00	1029.0	2248.00	4983.0	3209.0	838.389529	297.523566	301.0	560.00	840.0	1109.00	1439.0	3209.0	834.641945	305.702657	4.0	555.00	831.0	1103.00	1440.0	3209.0	912.298847	345.147642	1.0	675.00	901.0	1192.00	1439.0	3209.0	41.373013	8.079879	22.0	35.00	42.0	48.0	56.0	3209.0	60.414148	18.406963	10.0	49.00	60.0	72.00	97.0	3209.0	10.746650	4.811374	0.0	8.00	10.0	15.00	20.0	3209.0	3.264257	8.605621	0.0	0.0	0.0	0.0	38.0	3209.0	30.141670	2.574206e-01	29.51	30.000	30.130	30.3100	30.74	3209.0	31.121845	9.505992	0.0	26.00	30.0	37.00	53.0	3209.0	28.066999	7.941231	0.0	20.00	29.0	34.0	45.0	3209.0	20.628856	6.976157	7.0	15.00	19.0	25.00	41.0
Partly Cloudy / Windy	582.0	15.950172	83.769000	-11.0	-5.00	-2.0	10.00	1199.0	582.0	228.805842	127.154121	57.0	116.00	189.5	374.75	685.0	582.0	1292.400344	952.054159	94.0	427.00	1029.0	2422.00	4983.0	582.0	895.419244	238.841494	408.0	705.00	919.0	1065.00	1439.0	582.0	879.204467	251.972100	17.0	699.00	910.5	1061.00	1434.0	582.0	989.895189	306.904305	2.0	823.25	1042.0	1215.75	1439.0	582.0	40.580756	7.343280	19.0	37.00	40.0	45.0	67.0	582.0	49.414089	13.600218	27.0	40.00	48.0	57.00	86.0	582.0	24.225086	3.199482	21.0	22.00	23.0	26.00	36.0	582.0	30.522337	11.582021	0.0	31.0	33.0	36.0	47.0	582.0	29.983385	2.670681e-01	29.48	29.850	29.950	30.1400	30.67	582.0	30.702749	7.580387	1.0	27.00	30.0	36.00	47.0	582.0	30.998282	7.588945	2.0	28.00	32.0	37.0	45.0	582.0	22.781787	7.373405	9.0	17.00	22.0	28.00	41.0
Rain	351.0	14.495726	37.745605	-13.0	-4.00	0.0	17.50	283.0	351.0	231.165242	116.386406	59.0	134.00	194.0	365.00	685.0	351.0	1297.806268	872.571668	94.0	541.00	1069.0	2248.00	4983.0	351.0	929.364672	283.249165	301.0	722.50	965.0	1165.00	1370.0	351.0	943.860399	287.219827	296.0	729.00	985.0	1170.00	1369.0	351.0	1031.641026	349.125474	1.0	848.00	1138.0	1315.00	1439.0	351.0	45.045584	6.591178	33.0	40.00	46.0	51.0	54.0	351.0	21.598291	29.541369	10.0	10.00	10.0	10.00	97.0	351.0	11.193732	3.497275	5.0	8.00	12.0	14.00	18.0	351.0	3.019943	7.702849	0.0	0.0	0.0	0.0	25.0	351.0	29.935926	2.163758e-01	29.29	29.810	29.980	30.0900	30.21	351.0	31.173789	8.516605	0.0	28.00	30.0	40.00	51.0	351.0	29.997151	7.052253	4.0	24.00	33.0	35.0	43.0	351.0	24.014245	7.763086	10.0	18.00	22.0	30.00	41.0
Rain / Windy	25.0	3.800000	28.709754	-12.0	-7.00	-5.0	0.00	131.0	25.0	206.160000	99.117641	78.0	137.00	182.0	233.00	401.0	25.0	1149.240000	729.917591	187.0	636.00	944.0	1598.00	2475.0	25.0	825.560000	33.810846	749.0	810.00	821.0	839.00	890.0	25.0	829.360000	32.666088	774.0	803.00	822.0	853.00	885.0	25.0	1002.920000	67.448079	858.0	962.00	999.0	1047.00	1131.0	25.0	45.000000	2.500000	42.0	42.00	47.0	47.0	47.0	25.0	10.000000	0.000000	10.0	10.00	10.0	10.00	10.0	25.0	24.680000	2.749545	23.0	23.00	23.0	29.00	29.0	25.0	37.120000	1.810157	35.0	35.0	38.0	39.0	39.0	25.0	29.739200	3.290390e-02	29.70	29.700	29.760	29.7700	29.77	25.0	27.160000	2.477902	17.0	28.00	28.0	28.00	28.0	25.0	36.560000	4.011234	26.0	34.00	34.0	40.0	43.0	25.0	24.400000	6.658328	15.0	19.00	22.0	28.00	38.0
Snow	2.0	-4.000000	0.000000	-4.0	-4.00	-4.0	-4.00	-4.0	2.0	290.500000	133.643182	196.0	243.25	290.5	337.75	385.0	2.0	1771.500000	965.200756	1089.0	1430.25	1771.5	2112.75	2454.0	2.0	777.500000	3.535534	775.0	776.25	777.5	778.75	780.0	2.0	773.500000	3.535534	771.0	772.25	773.5	774.75	776.0	2.0	978.000000	9.899495	971.0	974.50	978.0	981.50	985.0	2.0	26.000000	0.000000	26.0	26.00	26.0	26.0	26.0	2.0	86.000000	2.828427	84.0	85.00	86.0	87.00	88.0	2.0	16.500000	2.121320	15.0	15.75	16.5	17.25	18.0	2.0	0.000000	0.000000	0.0	0.0	0.0	0.0	0.0	2.0	30.370000	1.414214e-02	30.36	30.365	30.370	30.3750	30.38	2.0	17.000000	0.000000	17.0	17.00	17.0	17.00	17.0	2.0	24.000000	0.000000	24.0	24.00	24.0	24.0	24.0	2.0	35.000000	4.242641	32.0	33.50	35.0	36.50	38.0
Wintry Mix	83.0	12.337349	28.247287	-10.0	-4.00	0.0	15.50	149.0	83.0	243.036145	135.684574	59.0	115.50	223.0	375.50	685.0	83.0	1423.734940	1025.365123	94.0	426.00	1521.0	2465.00	4983.0	83.0	1000.072289	270.940493	523.0	732.50	1155.0	1214.00	1439.0	83.0	995.060241	281.011255	33.0	744.00	1153.0	1208.00	1419.0	83.0	939.493976	442.534644	1.0	799.50	966.0	1340.50	1432.0	83.0	34.457831	1.337099	32.0	33.00	34.0	36.0	36.0	83.0	71.903614	20.802565	10.0	62.00	75.0	89.00	97.0	83.0	9.192771	5.246271	3.0	5.00	5.0	13.50	20.0	83.0	2.240964	6.904559	0.0	0.0	0.0	0.0	24.0	83.0	29.970964	2.849160e-01	29.47	29.825	30.170	30.2200	30.22	83.0	30.228916	7.697521	12.0	24.50	28.0	38.00	41.0	83.0	30.096386	7.566960	11.0	25.00	29.0	31.0	46.0	83.0	29.265060	7.829096	10.0	23.00	30.0	35.50	41.0
Wintry Mix / Windy	4.0	54.750000	75.716026	-2.0	10.00	28.0	72.75	165.0	4.0	276.250000	133.475029	150.0	167.25	274.0	383.00	407.0	4.0	1637.750000	1026.307418	740.0	755.00	1612.5	2495.25	2586.0	4.0	941.750000	73.035950	833.0	935.00	972.0	978.75	990.0	4.0	996.500000	10.661457	988.0	988.75	993.5	1001.25	1011.0	4.0	1113.000000	101.597244	983.0	1057.25	1133.5	1189.25	1202.0	4.0	34.500000	0.577350	34.0	34.00	34.5	35.0	35.0	4.0	53.000000	49.652123	10.0	10.00	53.0	96.00	96.0	4.0	22.500000	1.732051	21.0	21.00	22.5	24.00	24.0	4.0	29.500000	0.577350	29.0	29.0	29.5	30.0	30.0	4.0	29.485000	5.773503e-03	29.48	29.480	29.485	29.4900	29.49	4.0	32.000000	0.000000	32.0	32.00	32.0	32.00	32.0	4.0	38.000000	0.000000	38.0	38.00	38.0	38.0	38.0	4.0	39.000000	2.160247	36.0	38.25	39.5	40.25	41.0

	MONTH	DAY_OF_MONTH	DAY_OF_WEEK	CARRIER_CODE	FLIGHT_NO	DEST	DEP_DELAY	SCHEDULED_DURATION	DISTANCE	SCHEDULED_DEPARTURE	ACTUAL_DEP_TIME	SCHEDULED_ARRIVAL	Temperature	Dew Point	Humidity	Wind	Wind Speed	Wind Gust	Pressure	Condition	FLT_SCH_ARRIVAL	FLT_SCH_DEPARTURE	TAXI_OUT
20511	1	6	1	B6	N952JB	FLL	-8	185	1069	301	293	486	33	29	85	W	10	0	29.93	Cloudy	1	4	31
20512	1	6	1	B6	N973JT	SJU	-7	223	1598	301	294	584	33	29	85	W	10	0	29.93	Cloudy	1	4	29
20513	1	6	1	B6	N982JB	LAX	-3	386	2475	330	327	536	33	29	85	W	10	0	29.93	Cloudy	10	24	25
20514	1	6	1	DL	N110DU	SLC	-1	330	1990	330	329	540	33	29	85	W	10	0	29.93	Cloudy	10	24	34
20515	1	6	1	AA	N176UW	PHX	-3	365	2153	345	342	590	33	29	85	W	10	0	29.93	Cloudy	10	24	31
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
18414	12	29	7	B6	N317JB	BOS	18	70	187	1360	1378	1430	44	44	10	E	12	0	30.00	Light Rain	18	35	24
18415	12	29	7	AA	N117AN	BOS	-5	76	187	1390	1385	26	44	44	10	E	12	0	30.00	Light Rain	22	19	22
18416	12	29	7	B6	N957JB	SJU	0	225	1598	1412	1412	257	44	44	10	E	12	0	30.00	Light Rain	22	19	18
18417	12	29	7	DL	N994AT	TPA	244	190	1005	1169	1413	1359	44	44	10	E	12	0	30.00	Light Rain	22	19	10
18418	12	29	7	B6	N972JT	BQN	-9	224	1576	1438	1429	282	44	44	10	E	12	0	30.00	Light Rain	22	19	22

	MONTH	DAY_OF_MONTH	DAY_OF_WEEK	CARRIER_CODE	FLIGHT_NO	DEST	DEP_DELAY	SCHEDULED_DURATION	DISTANCE	SCHEDULED_DEPARTURE	ACTUAL_DEP_TIME	SCHEDULED_ARRIVAL	Temperature	Dew Point	Humidity	Wind	Wind Speed	Wind Gust	Pressure	Condition	FLT_SCH_ARRIVAL	FLT_SCH_DEPARTURE	TAXI_OUT
21543	1	9	4	9E	N907XJ	RDU	-5	128	427	535	530	663	26	9	49	NW	12	22	30.73	Fair	48	20	24
18923	12	31	2	9E	N820AY	IAD	37	100	228	1165	1202	1265	43	39	86	SSW	10	0	29.63	Cloudy	23	35	24
24783	1	19	7	9E	N8783E	BWI	-5	86	184	1160	1155	1246	36	18	48	WNW	16	0	29.89	Fair	38	28	14
9459	11	30	6	9E	N600LR	PIT	-8	106	340	454	446	560	32	21	64	N	10	0	30.09	Mostly Cloudy	36	31	28
24791	1	19	7	9E	N8974C	ORF	-3	107	290	1170	1167	1277	34	16	48	WNW	17	28	29.92	Fair	38	28	38
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
26031	1	23	4	YX	N133HQ	CMH	-10	121	483	933	923	1054	42	27	55	SSW	5	0	30.33	Cloudy	30	39	22
26026	1	23	4	YX	N404YX	IND	-11	143	665	930	919	1073	42	27	55	SSW	5	0	30.33	Cloudy	30	39	18
20165	1	4	6	YX	N214JQ	BOS	-2	89	187	1260	1258	1349	47	42	83	NW	18	26	29.53	Light Rain	35	43	39
20166	1	4	6	YX	N875RW	PIT	14	117	340	1250	1264	1367	47	42	83	NW	18	26	29.53	Light Rain	30	27	35
20295	1	5	7	YX	N201JQ	ROC	52	95	264	615	667	710	42	25	51	WNW	22	36	29.83	Mostly Cloudy / Windy	32	19	23

JFK Flight Delay Analysis

with Linear Regression

Linear Regression: Predicting Taxi-Out Delay¶

Given the dataset, predict the runway time of the flight.¶

Task Details¶

Some models to consider:-¶

Expected Submission¶

Evaluation¶

Configuring the Data Frame¶

Loading the data from csv file¶

Editing the column names for clarity¶

Preparing the Data for Analysis¶

Checking for and dropping missing values¶

Aggregating using: min, max, means, sum, distinct and count.¶

Ordering the dataset by: date (month, day of month, day of week), carrier_code¶

Dropping columns (dates, categorical data) for k-Fold Cross-Validation¶

k-Fold Cross-Validation (CV)¶

Splitting the dataset (90:10)¶

Linear Regression¶

Ridge Regression¶

Lasso Regression¶

K-nearest Neighbours¶

Support Vector¶

Naive Bayes¶

Random Forest¶

LightGBM (Tree Based Model)¶

	MONTH	DAY_OF_MONTH	DAY_OF_WEEK	OP_UNIQUE_CARRIER	TAIL_NUM	DEST	DEP_DELAY	CRS_ELAPSED_TIME	DISTANCE	CRS_DEP_M	DEP_TIME_M	CRS_ARR_M	Temperature	Dew Point	Humidity	Wind	Wind Speed	Wind Gust	Pressure	Condition	sch_dep	sch_arr	TAXI_OUT
0	11	1	5	B6	N828JB	CHS	-1	124	636	324	323	448	48	34	58	W	25	38	29.86	Fair / Windy	9	17	14
1	11	1	5	B6	N992JB	LAX	-7	371	2475	340	333	531	48	34	58	W	25	38	29.86	Fair / Windy	9	17	15
2	11	1	5	B6	N959JB	FLL	40	181	1069	301	341	482	48	34	58	W	25	38	29.86	Fair / Windy	9	17	22
3	11	1	5	B6	N999JQ	MCO	-2	168	944	345	343	513	48	34	58	W	25	38	29.86	Fair / Windy	9	17	12
4	11	1	5	DL	N880DN	ATL	-4	139	760	360	356	499	46	32	58	W	24	35	29.91	Fair / Windy	9	17	13

	DEP_DELAY	SCHEDULED_DURATION	DISTANCE	SCHEDULED_DEPARTURE	ACTUAL_DEP_TIME	SCHEDULED_ARRIVAL	Temperature	Dew Point	Humidity	Wind Speed	Wind Gust	Pressure	FLT_SCH_ARRIVAL	FLT_SCH_DEPARTURE
12992	-1	105	427	1030	1029	1135	31	17	57	3	0	30.71	32	32
27682	-3	187	740	970	967	1097	41	25	53	18	0	29.83	28	29
16171	-3	365	2153	345	342	590	35	31	85	8	0	30.14	11	21
15508	30	263	1521	1289	1319	52	27	15	61	10	0	30.63	32	35
4622	-14	192	1089	485	471	677	40	27	60	8	0	30.26	36	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
10955	-10	100	266	1320	1310	1420	39	25	57	15	30	30.02	29	32
17291	-2	292	1626	1015	1013	1187	45	40	82	14	0	30.36	28	32
5192	-5	412	2586	1199	1194	1431	34	5	30	10	0	30.46	40	26
12172	-2	384	2475	1320	1318	84	50	50	10	14	0	29.77	26	28
235	33	188	1069	1130	1163	1318	49	30	48	12	0	30.21	40	24

	DEP_DELAY	SCHEDULED_DURATION	DISTANCE	SCHEDULED_DEPARTURE	ACTUAL_DEP_TIME	SCHEDULED_ARRIVAL	Temperature	Dew Point	Humidity	Wind Speed	Wind Gust	Pressure	FLT_SCH_ARRIVAL	FLT_SCH_DEPARTURE
1637	-6	87	213	515	509	602	50	33	52	12	0	30.39	52	18
22484	-3	265	1391	539	536	744	62	49	62	25	0	29.98	49	18
14604	103	85	187	1034	1137	1119	34	34	10	12	0	29.71	38	36
5945	-11	379	2475	425	414	624	43	43	10	10	0	29.78	16	14
26858	0	125	427	516	516	641	40	35	83	13	0	29.83	47	17
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
4184	8	128	483	1220	1228	1348	30	7	38	9	0	30.43	29	44
938	-11	180	1005	447	436	627	44	36	73	3	0	30.37	35	28
25913	-7	395	2422	546	539	761	38	28	68	9	0	30.43	46	18
5549	-8	83	266	1320	1312	1403	39	31	73	17	0	30.07	32	34
8351	-8	188	1069	590	582	778	50	44	80	6	0	30.04	37	20